{"server":"com.scorecompute/scorecompute","count":50,"changes":[{"tool":"tour_profile","kind":"added","observed_at":"2026-10-05T03:14:34.520Z","fields":[],"description_before":null,"description_after":"Locally normalized geometric descriptors of 3–256 planar points: distances, nearest-neighbour isolation, centroid spread, PCA collinearity and histogram. The principal-axis mirror residual is null for isotropic noncoincident covariance, whose axes are undetermined. Rounded fingerprints are descriptive, not proofs of equivalence or method benefit.","description_similarity":null,"before_hash":null,"after_hash":"c1f1d8673c9bdd20b756665df55e7880"},{"tool":"scan_counterexample","kind":"added","observed_at":"2026-10-05T03:14:34.520Z","fields":[],"description_before":null,"description_after":"Bounded deterministic float64 scan of a scalar <= or >= claim over a declared grid of 1–6 variables. Reports numerical witnesses, undefined and uncertain evaluations, and the exact stop reason. A propagated screening guard rejects near-boundary candidates; it is not a certified interval or formal proof. An inconclusive outcome preserves unresolved sampled cells; absence of a witness does not establish the claim over the continuous box.","description_similarity":null,"before_hash":null,"after_hash":"e9204a24bb5bdc4be6d423d2d91f72c4"},{"tool":"shape_the_sound","kind":"added","observed_at":"2026-10-04T21:14:12.991Z","fields":[],"description_before":null,"description_after":"Kac's question in reverse: design a polygonal drumhead whose lowest tones play requested frequency ratios (a fifth, a triad, a pentatonic scale), each accepted within ±tolerance_cents. proven_impossible is returned only when proven theorems exclude every ratio combination inside those tolerance windows for a connected uniform membrane with a fixed edge: simple fundamental, f2/f1 ≤ j11/j01 ≈ 1.5933 with equality for the disk (Ashbaugh–Benguria 1992), and Yang's universal inequality minimized exactly over the window box; an exact-target exclusion is reported separately. Otherwise multi-start L-BFGS with exact finite-element shape derivatives designs a 5–16-vertex polygon, then reanalyses it on three refined meshes with the shared hear_the_shape solver: achieved ratios, errors in cents with estimated uncertainty (not rigorous bounds), resolution warnings, optional numerical tuning of the fundamental in Hz. not_achieved is a bounded-search result, never an impossibility proof. Ideal membrane only.","description_similarity":null,"before_hash":null,"after_hash":"5053c34e7aa3e22a657e6b1d0ee854bb"},{"tool":"verify_claim","kind":"added","observed_at":"2026-10-02T02:51:49.178Z","fields":[],"description_before":null,"description_after":"Verify a structured arithmetic, shadow, ephemeris, statistics or route claim with a bounded native engine. Returns a model-scoped verdict and portable Ed25519 server receipt; never truth, authenticity or fraud certification. Route claims explicitly distinguish optimality from a supplied tour total. Native failures return no scientific verdict. Parameters and examples: /verify and /docs/mcp/.","description_similarity":null,"before_hash":null,"after_hash":"93d34b50e87ea3899b1139a8762b40fb"},{"tool":"check_arithmetic","kind":"added","observed_at":"2026-10-02T02:51:49.178Z","fields":[],"description_before":null,"description_after":"Check an explicit arithmetic claim. Checked i128 rationals give exact verdicts when expression, claim and tolerances are representable. Unsupported functions or overflow return an estimate with an undetermined verdict. Includes a versioned integrity digest; no checks of units or model meaning.","description_similarity":null,"before_hash":null,"after_hash":"27ce13a545e6e3454755568fbb4f5988"},{"tool":"propagate_uncertainty","kind":"added","observed_at":"2026-10-01T21:08:41.553Z","fields":[],"description_before":null,"description_after":"Check dimensions, then compare first-order GUM with seeded fixed-sample Monte Carlo for an explicit model of 1–16 inputs. Return uncertainty budgets, coverage intervals and convergence/linearization findings. Conditional on supplied distributions; no affine units. CPU, direct-only; no planner binding.","description_similarity":null,"before_hash":null,"after_hash":"6dd98c6e9070643b24804ae134eebddb"},{"tool":"kepler_stability","kind":"added","observed_at":"2026-10-01T21:08:41.553Z","fields":[],"description_before":null,"description_after":"Survey up to 512 initial orbits in a planar circular Sun–Jupiter model; at most 4 million reserved CPU steps. Return finite-window sensitivity, actual durations, sampled Jacobi drift and explicit stops. Bands do not prove chaos or stability; radial overlap is not an encounter. Direct-only.","description_similarity":null,"before_hash":null,"after_hash":"87f9549fe6db811b88a96af9fd299fbb"},{"tool":"hear_the_shape","kind":"added","observed_at":"2026-10-01T21:08:41.553Z","fields":[],"description_before":null,"description_after":"Compute 1–12 ideal fixed/free membrane modes for a simple polygon in metres using bounded P1 finite elements. Return upper bounds, extrapolated estimates and optional frequencies/shapes. Finite spectral agreement does not prove isospectrality; no damping. CPU, direct-only; no planner binding.","description_similarity":null,"before_hash":null,"after_hash":"02b0a79f27d7ac5c2b35f069a29a8aea"},{"tool":"compute_orbit","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description","inputSchema","outputSchema"],"description_before":"Compute an ideal elliptical orbit around one solar mass. Time is measured from periapsis and distances are in astronomical units. This two-body model is not a real celestial ephemeris.","description_after":"Compute an ideal two-body Keplerian orbit around one solar mass. Time starts at periapsis; distances use AU and time uses days. This model is not a real celestial ephemeris.","description_similarity":0.611,"before_hash":"18acc2468b4678937aafff9574533a7a","after_hash":"6adc66cb2900dac74fa0400713452001"},{"tool":"get_network_job","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Read one public contributor ticket and verified progress. Completed pi jobs contain estimate; completed schedule jobs have estimate/inside null and report successes, probability and a fixed-sample Wilson95 interval under the declared discrete synthetic model. A model probability does not establish real completion. Worker-reported elapsed time, coordinator verification time and total wall time remain separate. Each shard counts once; expired or duplicate results are rejected. No private user data is accepted.","description_after":"Read a public contributor ticket/progress and verified pi or discrete synthetic schedule result. Schedule results include fixed-sample Wilson95 bounds. Worker/verification/wall times are separate; model probabilities are not delivery guarantees.","description_similarity":0.348,"before_hash":"0bec38bbf2815837f4f05826eeaabaa2","after_hash":"010826b3bd17b5998a8bf808ec5a0716"},{"tool":"submit_network_job","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Queue a public synthetic compiled Monte Carlo job on consenting contributor clients. pi_chunk_v1 uses the fixed 31-bit integer circle model on CPU/CUDA, distinct from simulate_pi. schedule_probe_v1 is CPU-only and requires one of three compiled scenarios; each task samples a 65536-point midpoint grid with ±25% duration variation, distinct from continuous simulate_plan. No custom durations, files or private datasets are accepted. Returns a ticket, not a result; poll get_network_job. Every accepted shard is fully recomputed on coordinator CPU; no net speedup claim. Workers may be unavailable and jobs may expire.","description_after":"Queue fixed public synthetic pi (CPU/CUDA) or one of three discrete schedule scenarios (CPU only). No private data/custom code. Returns a ticket; poll get_network_job. Coordinator recomputes every accepted shard; no net speedup claim. Jobs may expire.","description_similarity":0.4,"before_hash":"75c26745cb5452d279a512072aa181e3","after_hash":"d47cd59ec20fa0d4a13cc2d99fd81bba"},{"tool":"network_status","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Read the live contributor pilot: available and busy GPUs, explicitly offered CPU threads, worker supported_workloads, stale workers and verified sample throughput broken down by workload. Aggregate samples mix different calculations and are not a performance comparison. Hardware is reported, not attested. VRAM is separate per GPU, not a shared memory pool. This does not add the legacy worker inventory a second time.","description_after":"Read contributor availability, offered CPU/GPU resources and verified throughput by workload. Hardware is self-reported; per-GPU VRAM is not pooled. Mixed-workload samples do not measure comparative speed.","description_similarity":0.274,"before_hash":"85d7706b5e909923ea8fd387957de978","after_hash":"29fc809f7b3aab3c60bdac9bc7bf6966"},{"tool":"execute_composition","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Recompile and execute an approved optimize_tasks → selected_durations.v1 → simulate_plan or route_optimizer → route_durations.v1 → simulate_plan path in Rust. Supply the engine arguments plus simulate_plan configuration (budget, uncertainty, samples, seed; omit durations). The route path also requires adapters[\"route_durations.v1\"].speed_kmh from 1 to 150, explicit independent-uniform assumptions and 1–32 nonzero route legs. Whole-minute durations use ceil(distance_km / speed_kmh * 60). Shared 1–1440 minute budget, each duration 1–1440 minutes, 100–20000 fixed samples. Geometric distance and a declared speed are not road or traffic predictions. Return the engine result, a model-conditional risk assessment, a 95% Hoeffding sampling interval and real native events. Completed means the assessment ran, not that the deadline is safe. Other graph paths must use their advertised existing tool or remain planning-only.","description_after":"Run approved task-selection/route-to-duration risk chains only. Supply engine inputs and explicit uncertainty; route speed is 1–150 km/h. Returns native receipts and 95% sampling bounds. Completed means assessed, not safe. Other paths use advertised bindings.","description_similarity":0.245,"before_hash":"42f1eee890dbf510c5b025d646c679ab","after_hash":"77ea09f339c7285d55be0992f97895f8"},{"tool":"compose_capabilities","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Let native Rust compose a dependency plan from goal contracts and declared available contracts. Enforce allowed tools, locality, step and search limits. Return the selected graph, examined alternatives, blockers, search completeness and any existing-tool execution binding. Structural cost counts registered graph steps; it is not measured runtime, financial cost or scientific quality. Available facts are declarations; actual arguments are validated at execution. No engines run during planning.","description_after":"Plan from declared available/goal contracts within tool, locality and search bounds. Returns dependencies, blockers and existing-tool bindings. Cost counts graph steps, not speed, price or quality. Runs no engines; execution validates arguments.","description_similarity":0.338,"before_hash":"ba77d6a1246a5f1699242d7eada302cd","after_hash":"9f13816254422535de2e0790381f5b23"},{"tool":"list_composition_capabilities","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Read the trusted native bank of versioned semantic contracts, engine capabilities, explicit adapters, composite capabilities and reproducible planning examples. Each individual MCP engine remains independently callable. This catalogue contains implemented capabilities only; unsupported model/unit facts explain missing adapters. No computation is executed.","description_after":"Read implemented versioned contracts, native capabilities, approved adapters and planning examples. Unsupported unit/model facts expose missing adapters. No engines run; direct tools remain independently callable.","description_similarity":0.391,"before_hash":"2638246778ed02ad698da762c0f562fc","after_hash":"37c69f5428b6bf3257e3602b164b9cff"},{"tool":"build_robust_plan","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Compare up to three task selections in native Rust using optimize_tasks and, when needed, simulate_plan. Select the highest-value examined candidate whose simultaneous 95% Monte Carlo lower bound meets the requested success target under independent uniform duration uncertainty. Use an exact bound instead of simulation when possible and reuse identical selections within this mission. Return inconclusive if none passes, or blocked for unsupported contracts. Streams actual native events via MCP progress; one composite MCP call, no arbitrary tool generation.","description_after":"Compare up to three task selections; choose highest examined value meeting the target under simultaneous 95% sampling bounds or an exact bound. Independent-uniform durations; can return inconclusive/blocked. Streams native events.","description_similarity":0.325,"before_hash":"b8ed256ba192f31d476f3d46d1ca9a74","after_hash":"78113e84948e178e913457ce400bc938"},{"tool":"plan_mission","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Preview a bounded robust scheduling mission without executing engines. Validate explicit duration assumptions and local tool permissions, then return up to three candidate budgets (nominal, 10% reserve, 20% reserve), bounds on engine calls and samples, or explicit blockers. Does not generate arbitrary tools or execute external code.","description_after":"Preview robust scheduling without running engines: validate assumptions/permissions and return up to three candidate budgets (nominal, 10% reserve, 20% reserve), compute limits or blockers. No arbitrary tools or external code.","description_similarity":0.532,"before_hash":"dc3a9a0ba77d02eb03fc8330b9420046","after_hash":"c3f4a0394e2e4fd287a5913b0406d138"},{"tool":"list_capabilities","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Inspect the fourteen base native tool contracts, themes, units, assumptions, execution backends and composition readiness. MCP tools/list discovers all direct tools; list_composition_capabilities includes the additional complete-request bindings for triangulation and Discovery. Optional exact theme filter. The scheduling family compares task selections; approved selection_risk and route_risk chains use explicit adapters and simulate_plan. All tools remain independently callable.","description_after":"Read native contracts, themes, units, assumptions, backends and approved composition families; optional exact theme filter. tools/list discovers direct MCP tools; list_composition_capabilities adds planner bindings.","description_similarity":0.357,"before_hash":"ba7be40eb947491923403f3c3becc0e4","after_hash":"19e7d84bc214e811aef6cbb6369d2526"},{"tool":"improve_schedule","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Compare up to 32 predeclared combinations of deadline extensions and optional-task removals while preserving every required task. Caller supplies costs per extra minute and lost value, maximum change cost, an independent-uniform duration model, success target and fixed sample count. Search uses simultaneous Hoeffding bounds and selects the lowest-cost search-qualified examined candidate; one separately seeded confirmation can accept or decline it without retrying another candidate. Exact model bounds avoid fabricated Monte Carlo results. Return confirmed, confirmation_inconclusive or target_not_demonstrated, candidate costs, search and confirmation receipts. Minimality is limited to the supplied search-qualified alternatives; confirmed is conditional on the mathematical duration model, not real-world delivery reliability. Independently callable Rust CPU tool.","description_after":"Compare up to 32 declared deadline/optional-task changes under independent-uniform durations; preserve required tasks. Search bounds select one finalist for separately seeded confirmation, without retries. Conditional on the model, not delivery reliability.","description_similarity":0.24,"before_hash":"f19a83f6036e1f10cb2024cf68d9cc78","after_hash":"4a034dd3d5aa4dd37e6fa6bacd45ce95"},{"tool":"stress_test_observation","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Search 1–32 supplied hypothetical angular-bias/clock-correction perturbations for counterexamples to a declared reconstruction-stability claim. Rust fits the original observations, applies each bounded perturbation to one observer, and refits the same spherical constant-velocity model. A counterexample can violate the position-shift limit or the requirement for a usable consistent fit; solver non-convergence remains inconclusive. Return evaluated cases, native fits, first counterexample and explicit budget/refusal status. none_found applies only to examined admissible cases, never global robustness or an object-identification conclusion. No new observations or independent scientific corroboration are acquired. Explicit hypothetical acknowledgement is required. Independently callable CPU tool; an optional composition binding passes the complete validated request, never an invented observation.","description_after":"Refit 1–32 declared hypothetical angular/clock perturbations to challenge reconstruction stability. Explicit hypothetical acknowledgement required. Non-convergence is inconclusive; none_found covers examined cases only. No new observations.","description_similarity":0.253,"before_hash":"654096806eb6520df1df397f5ee6f39a","after_hash":"beccb9b967859fc0bb2f9f5b67a2afde"},{"tool":"assimilate_observation","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Refit original angular observations together with one explicitly supplied new angular series. Rust computes the baseline itself, uses its mean only as an initialization, and includes every original/new angular pair once without adding the baseline covariance as a prior. New timestamps are already clock-corrected and must follow the baseline; existing stations retain coordinates and angular noise. Return baseline and updated native fits plus conditional before/forecast/refit uncertainty at one common horizon, or an explicit rejection. A mean-position shift is not error against known truth; new data may contradict the model or worsen uncertainty. The caller must declare data_origin synthetic or measured; neither declaration is authenticated. No hidden truth, client baseline/covariance or forecast-only angles are generated by this tool. Independently callable Rust CPU tool.","description_after":"Refit original tracks plus one supplied new angular series, each counted once; compute the baseline natively. Declare synthetic/measured origin (unverified). Conditional uncertainty may worsen; forecast angles are not acquired evidence.","description_similarity":0.23,"before_hash":"4c8c66dd47b52d122d04f8d5977459a9","after_hash":"10b0c007b0e9d2192ec5e06b435ea0fa"},{"tool":"plan_observation","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Fit original angular observations in Rust, then rank 1–64 proposed observation series by predicted position uncertainty at one common corrected-time horizon. Each candidate supplies a station, 3–120 future times, angular standard deviations and a declared cost, never candidate angles or a client-supplied baseline/covariance. Existing stations use observer_1, observer_2, etc. The local linear information update assumes independent new errors, exact stations/clocks and constant velocity in spherical ECEF. Returns the real baseline fit and conditional forecasts, or baseline_rejected; predicted does not mean a new measurement was acquired or that an admissible candidate exists. Ranking is only over supplied candidates, and geometric elevation does not establish terrain visibility or sensor availability. Independently callable CPU tool; an optional composition binding passes the complete validated request, never an invented observation.","description_after":"Fit original tracks, then rank 1–64 supplied future series by local-linear uncertainty and declared cost. Assumes constant velocity, independent new errors and exact stations/clocks. Candidate angles and client baselines are forbidden. Prediction is not an acquired measurement or visibility proof.","description_similarity":0.318,"before_hash":"1141910bffe177525182a96a78696183","after_hash":"64938bf62cc93fc76232138fdb20030d"},{"tool":"triangulate_tracks","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Estimate a single moving object’s 3D position and velocity from geometric azimuth/elevation tracks supplied by 2–4 stationary observers. Bounded Rust CPU weighted least squares assumes constant velocity in a spherical Earth-fixed frame (R=6371.0088 km), declared angular standard deviations and supplied fixed clock offsets. Returns estimated, inconsistent, degenerate or no_convergence, component standard deviations, trajectory and observer residuals. No refraction correction or automatic image analysis; a reduced chi-square cutoff of 9 is a screening convention. Local uncertainties are conditional on the model, not calibrated real-world accuracy. Does not identify the object or its origin. Independently callable; the composition planner can also bind its complete request.","description_after":"Fit position/velocity from 2–4 supplied azimuth/elevation tracks using constant velocity in spherical ECEF and declared angular noise/clocks. Reports fit status and conditional local uncertainty; no object identification or calibrated accuracy.","description_similarity":0.214,"before_hash":"2bc9287f2ed5f10614f5f6eef36f9581","after_hash":"e6cc33203d3833d38a4990a5d094d75f"},{"tool":"plan_golden_hour","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Compute golden [-4,+6 degrees] and blue [-6,-4 degrees] photographic windows for the geometric solar centre during one strict UTC day [00:00, next 00:00), without refraction. Input must be a real Gregorian midnight from 1900 through 2100, latitude -89..89 and East-positive longitude -180..180. Return UTC millisecond windows and threshold crossings, unrounded solver durations, midpoint azimuths when defined, day extrema, boundary-clipped flags and bounded numerical work. Sunrise/sunset crossings at geometric -0.833 degrees use a separate convention, not official refracted upper-limb sunrise. Absent windows are valid empty results. Terrain, buildings, clouds, weather and lighting quality are not modelled. Numerical search tolerance is not astronomical uncertainty; oracle fixtures cover reference dates, not the entire accepted year range. Uses the same solar primitives as shadow and ephemeris engines, so combined results are not independent corroboration. Independently callable Rust CPU tool; a complete-request composition binding requires no invented adapter.","description_after":"Compute geometric golden [-4,+6°] and blue [-6,-4°] windows for one UTC day, 1900–2100. Sunrise at -0.833° is a separate convention. No refraction, terrain or weather. Numerical tolerance is not astronomical accuracy; oracle validation covers reference dates only. Shared solar models are not independent corroboration.","description_similarity":0.289,"before_hash":"1cc06687c432d05900d071b56e31b2ea","after_hash":"e0713753390b379a380776f31e3b6e06"},{"tool":"run_route_policy","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Execute an explicitly supplied experimental score AST on 2–128 Euclidean kilometre points. Closed tour, fixed depot 0, bounded construction and fixed 2-opt; complete permutation and geometric cost are checked. Exact=false: no optimum or superiority claim. Same bounded grammar as forge_route_policy; expressions are data with no code, URL, file or external effects. No retraining or automatic promotion. Original and compiled artifact hashes identify programs, not independent validation or trust. Version 0.2 compiles conservative simplifications and prepares only required features; converged semantics are preserved, but versioned fuel accounting means interrupted runs can differ. The standard route_optimizer remains separately available.","description_after":"Execute a supplied bounded score AST on 2–128 Euclidean-km points with depot 0 and 2-opt. Validates the closed tour; exact=false. No retraining, external effects or promotion. Hashes identify programs, not independent validation.","description_similarity":0.352,"before_hash":"f49de36c72b81886d4b8fbbac2566bcf","after_hash":"59aa50c4c56e4e7d4413263231838adf"},{"tool":"forge_route_policy","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Generate, mutate and cross bounded arithmetic route-construction rules in Rust using only supplied training cases. 1–8 closed Euclidean kilometre cases of 2–32 points, at most 64 attempted ASTs. Fixed depot 0 and bounded 2-opt; grammar has five declared features, discrete constants and add/sub/mul/min/max, at most 31 nodes and four edges deep. Complete journal records ancestry, failed and reused candidates; selects by mean training length ratio plus 0.01 times positive excess mean logical-fuel ratio, then worst ratio, total fuel, compiled size, original size and index. Only converged candidates with worst training ratio at most 1.10 are admitted. Fuel is a work proxy, not CPU cycles. Version 0.2 compiles conservative simplifications and reports original/compiled hashes and required features. No held-out validation, automatic promotion, arbitrary code or optimizer replacement. Download the complete receipt before independently validating one locked candidate. Public host stops between trials after 25 s; per-case work and time are capped. Independently callable CPU tool.","description_after":"Train route-score ASTs on 1–8 supplied cases: at most 64 attempts and 31 nodes; stop between trials after 25s. Select converged candidates using training quality plus logical-fuel cost, a work proxy rather than CPU time. No held-out validation, arbitrary code or automatic promotion.","description_similarity":0.255,"before_hash":"708531b02e12638d233698a96e75e816","after_hash":"707ade7489bad3bfd1fc6c116625b8f0"},{"tool":"route_optimizer","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Order 2–256 supplied points from fixed start index 0, with an optional return. Explicit planar kilometres or great-circle kilometres on a 6371.0088 km sphere. CPU Held–Karp certifies the numerical optimum only after complete search for at most 13 points; larger instances use bounded nearest-neighbour and 2-opt heuristics. Returns every leg, exact flag, stopping reason, measured time and work. Geometric distances only: no roads, traffic or travel-time forecasts. Callable independently of the orchestrator.","description_after":"Order 2–256 points from index 0 using planar or spherical kilometre distances. Exact only after completed Held–Karp search (at most 13 points); otherwise bounded heuristics. Returns every leg and stop reason. No roads or traffic.","description_similarity":0.377,"before_hash":"c3d7d7cfd6099974b9338ce6629395c1","after_hash":"26af2e5309e85cd8471daceb8d9007b8"},{"tool":"simulate_plan","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Test a task plan, including one produced by optimize_tasks, using independent bounded uniform duration variations. Return the probability of meeting the budget, mean duration and empirical 95th percentile. This illustrative uncertainty model is not a forecast guarantee.","description_after":"Estimate deadline success, mean duration and empirical p95 for up to 32 integer-minute tasks under independent bounded uniform duration variations. Seeded CPU sampling; not a real-world forecast guarantee.","description_similarity":0.255,"before_hash":"008bf4cdce570a5758c79a87aee38497","after_hash":"8b0a64b1743b22f548783d4fbcf43752"},{"tool":"screen_wash_trading","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Screen a supplied trade series for repeated volume at nearly identical prices within a bounded time window. Report recycled-volume ratio and cycle count. This is a pattern to examine, not proof of wash trading or an accusation.","description_after":"Screen a supplied trade series for repeated volume at nearly equal prices within a declared time window. Return recycled-volume ratio and cycles; a pattern does not prove wash trading.","description_similarity":0.512,"before_hash":"baa0bb7831d2cc1813c166a4a5eb6241","after_hash":"beca614f5e40fcb364003dfd551ebe9c"},{"tool":"analyze_chess_game","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Compare supplied chess positions and played moves against Stockfish UCI: first-choice agreement and centipawn loss per position. Accept SAN or UCI moves. Returns a statistical profile, never a cheating verdict. The complete analysis has a 25-second deadline.","description_after":"Compare 4–40 supplied FEN positions and played SAN/UCI moves with Stockfish: first-choice agreement and centipawn loss. Entire analysis has a 25-second deadline; no cheating verdict.","description_similarity":0.55,"before_hash":"5987dec6b5f83bd1117a1e2563bd8698","after_hash":"f1deecfd7c3d5d75d39a2e7b647e23df"},{"tool":"solve_equilibrium","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Solve Kuhn poker with CFR+ self-play and measure exploitability using pure best responses. Compare the game value against the analytical reference -1/18. An illustrative game-theory solver, not gambling advice.","description_after":"Solve Kuhn poker with CFR+ self-play, measure exploitability with pure best responses and compare the game value with -1/18. Illustrative game theory, not gambling advice.","description_similarity":0.8,"before_hash":"52d17f8a3e33991dcf24531a5f2dbe85","after_hash":"1429021ea439a00763e922aefc3e89c3"},{"tool":"check_shadow_track","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Compare measured shadow azimuths over time with the expected solar ephemeris. Check slope, time-lapse speed, rotation direction and individual residuals. Inputs are measured minute/azimuth pairs, not video files. Returns compatible, contredit or intestable.","description_after":"Compare 4–120 measured minute/azimuth pairs with solar motion: residuals, slope, direction and time-lapse speed. Supply measurements, not video. Results are model-conditional consistency findings.","description_similarity":0.395,"before_hash":"cc01cb7f2eb23a54d8a4d8558f4dc755","after_hash":"ac780669dac3e092b0cfdb03a18262a5"},{"tool":"analyze_kinematics","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Convert observed angular speed into minimum transverse speed at candidate distances using v = angular speed times distance. Compare illustrative balloon, drone, aircraft and satellite limits and check a claimed speed-distance pair. Makes no claim about object origin.","description_after":"Convert angular speed and candidate distances to minimum transverse speeds; check a claimed speed-distance pair. Distance hypotheses are supplied, not measured; no object-origin conclusion.","description_similarity":0.4,"before_hash":"b182f7d7378544d3d9cfd704866e4fde","after_hash":"bc80538f41d69ef3d230131dd4b43625"},{"tool":"audit_statistics","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Apply necessary GRIM/GRIMMER arithmetic consistency checks to reported statistics for bounded integer observations. Examine rounded means and sample standard deviations. Passing the filters is not proof that a dataset exists; an inconsistency is not evidence of fraud.","description_after":"Apply necessary GRIM/GRIMMER checks to rounded means and sample deviations of bounded integer observations. Passing does not prove a dataset exists; inconsistency does not establish fraud.","description_similarity":0.564,"before_hash":"f7a94cac99ef112a5f00b202458c32af","after_hash":"0ee7a52072f679f8c4580352376b6096"},{"tool":"check_ephemeris","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Check a claimed Sun or Moon position for a UTC date and location. Uses NOAA/Meeus approximations, topocentric lunar parallax, angular separation and lunar phase. The object parameter uses soleil (Sun) or lune (Moon). Returns compatible, contredit or intestable.","description_after":"Check a claimed Sun (soleil) or Moon (lune) position for UTC time/location using NOAA/Meeus approximations and lunar parallax. Returns model-conditional angular consistency and lunar phase.","description_similarity":0.583,"before_hash":"b3ff3fa7b7f1d8a56e4fb2d185ea39ab","after_hash":"131926cc898158ffc126bd1a2e3f8bb6"},{"tool":"verify_shadows","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Check solar-shadow consistency from supplied image measurements: NOAA solar position, ground-plane homography from 4 to 16 control points, and Monte Carlo uncertainty. Returns compatible, contredit or intestable under the stated assumptions; never an image-authenticity verdict.","description_after":"Check measured shadows using NOAA solar position, a ground-plane homography from 4–16 controls and Monte Carlo uncertainty. Returns conditional consistency, never image authenticity.","description_similarity":0.463,"before_hash":"3630394173d22ea17ca87a95b25d206e","after_hash":"b9f528bec09b954c67e94fc8c77b63d5"},{"tool":"optimize_tasks","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Select independent tasks exactly to maximize their total value within an integer-minute time budget. Each task can be selected once; at most 32 tasks.","description_after":"Exactly maximize value for up to 32 independent, indivisible tasks within an integer-minute budget. Each task is selected at most once; no prerequisites or shared resources.","description_similarity":0.545,"before_hash":"a5dc4d49a8f7b89c3d6f047025107bb5","after_hash":"bbaad5c30f8db007fb3e6b730a941ac4"},{"tool":"simulate_pi","kind":"changed","observed_at":"2026-10-01T15:04:46.200Z","fields":["description"],"description_before":"Estimate pi with reproducible Monte Carlo sampling and a 95% Wilson interval. Select CPU or CUDA; at most 5 million points. CUDA acceleration is available for this tool only.","description_after":"Estimate pi with seeded Monte Carlo and a 95% Wilson interval; up to 5 million samples. CPU or optional CUDA. Other direct scientific engines run on CPU.","description_similarity":0.385,"before_hash":"3f0049af7c6bc6996dc116f0375866ad","after_hash":"280d156f1fa13ad7724b3cdc7339f60e"},{"tool":"get_network_job","kind":"changed","observed_at":"2026-10-01T08:47:34.143Z","fields":["description"],"description_before":"Read one contributor job ticket and its verified progress or final pi_chunk_v1 receipt. Only completed jobs contain a final estimate. Counts aggregate each verified shard once, with expired leases rejected. The publicly visible job contains only synthetic sampling parameters, never private user data.","description_after":"Read one public contributor ticket and verified progress. Completed pi jobs contain estimate; completed schedule jobs have estimate/inside null and report successes, probability and a fixed-sample Wilson95 interval under the declared discrete synthetic model. A model probability does not establish real completion. Worker-reported elapsed time, coordinator verification time and total wall time remain separate. Each shard counts once; expired or duplicate results are rejected. No private user data is accepted.","description_similarity":0.321,"before_hash":"f53963e9aa6aaf41ad557b267049ab4e","after_hash":"0bec38bbf2815837f4f05826eeaabaa2"},{"tool":"submit_network_job","kind":"changed","observed_at":"2026-10-01T08:47:34.143Z","fields":["description","inputSchema"],"description_before":"Queue a public synthetic Monte Carlo pi_chunk_v1 job on consenting contributor clients. This is the fixed 31-bit integer model, distinct from simulate_pi. No files or private datasets are accepted. Returns a ticket: queued is not completed. Poll get_network_job for the result. Every accepted shard is recomputed on coordinator CPU for verification; no net acceleration claim. Workers may be unavailable and jobs may expire.","description_after":"Queue a public synthetic compiled Monte Carlo job on consenting contributor clients. pi_chunk_v1 uses the fixed 31-bit integer circle model on CPU/CUDA, distinct from simulate_pi. schedule_probe_v1 is CPU-only and requires one of three compiled scenarios; each task samples a 65536-point midpoint grid with ±25% duration variation, distinct from continuous simulate_plan. No custom durations, files or private datasets are accepted. Returns a ticket, not a result; poll get_network_job. Every accepted shard is fully recomputed on coordinator CPU; no net speedup claim. Workers may be unavailable and jobs may expire.","description_similarity":0.598,"before_hash":"f52f6e77ced737de6a94aaca12ab8dd5","after_hash":"75c26745cb5452d279a512072aa181e3"},{"tool":"network_status","kind":"changed","observed_at":"2026-10-01T08:47:34.143Z","fields":["description"],"description_before":"Read the live contributor pilot: available and busy GPUs, explicitly offered CPU threads, stale workers and observed verified pi_chunk_v1 throughput. Hardware is reported, not attested. VRAM is separate per GPU, not a shared memory pool. This does not add the legacy worker inventory a second time.","description_after":"Read the live contributor pilot: available and busy GPUs, explicitly offered CPU threads, worker supported_workloads, stale workers and verified sample throughput broken down by workload. Aggregate samples mix different calculations and are not a performance comparison. Hardware is reported, not attested. VRAM is separate per GPU, not a shared memory pool. This does not add the legacy worker inventory a second time.","description_similarity":0.667,"before_hash":"90a43ae3fe50d7c6765ac64e94ac1d91","after_hash":"85d7706b5e909923ea8fd387957de978"},{"tool":"execute_composition","kind":"changed","observed_at":"2026-10-01T08:47:34.143Z","fields":["inputSchema"],"description_before":null,"description_after":null,"description_similarity":null,"before_hash":"b591f61a25bbbe706d2410d800e20416","after_hash":"42f1eee890dbf510c5b025d646c679ab"},{"tool":"compose_capabilities","kind":"changed","observed_at":"2026-10-01T08:47:34.143Z","fields":["inputSchema"],"description_before":null,"description_after":null,"description_similarity":null,"before_hash":"8c741ce36a1c7f07dfe3bbde4ecd38de","after_hash":"ba77d6a1246a5f1699242d7eada302cd"},{"tool":"build_robust_plan","kind":"changed","observed_at":"2026-10-01T08:47:34.143Z","fields":["inputSchema"],"description_before":null,"description_after":null,"description_similarity":null,"before_hash":"de1079d00994e2c81d090d83ff3c68cb","after_hash":"b8ed256ba192f31d476f3d46d1ca9a74"},{"tool":"plan_mission","kind":"changed","observed_at":"2026-10-01T08:47:34.143Z","fields":["inputSchema"],"description_before":null,"description_after":null,"description_similarity":null,"before_hash":"ae4f37fd1dff88d4320c8e7163183571","after_hash":"dc3a9a0ba77d02eb03fc8330b9420046"},{"tool":"list_capabilities","kind":"changed","observed_at":"2026-10-01T08:47:34.143Z","fields":["description"],"description_before":"Inspect the thirteen native composition-bank tool contracts (triangulate_tracks is independently callable but not yet in this bank), themes, units, assumptions, execution backends and composition readiness. Optional exact theme filter. The scheduling family compares task selections; approved selection_risk and route_risk chains use explicit adapters and simulate_plan. All tools remain independently callable.","description_after":"Inspect the fourteen base native tool contracts, themes, units, assumptions, execution backends and composition readiness. MCP tools/list discovers all direct tools; list_composition_capabilities includes the additional complete-request bindings for triangulation and Discovery. Optional exact theme filter. The scheduling family compares task selections; approved selection_risk and route_risk chains use explicit adapters and simulate_plan. All tools remain independently callable.","description_similarity":0.597,"before_hash":"182bf7b2785e2c091c34ea31b4aae1e3","after_hash":"ba7be40eb947491923403f3c3becc0e4"},{"tool":"improve_schedule","kind":"added","observed_at":"2026-10-01T08:47:34.143Z","fields":[],"description_before":null,"description_after":"Compare up to 32 predeclared combinations of deadline extensions and optional-task removals while preserving every required task. Caller supplies costs per extra minute and lost value, maximum change cost, an independent-uniform duration model, success target and fixed sample count. Search uses simultaneous Hoeffding bounds and selects the lowest-cost search-qualified examined candidate; one separately seeded confirmation can accept or decline it without retrying another candidate. Exact model bounds avoid fabricated Monte Carlo results. Return confirmed, confirmation_inconclusive or target_not_demonstrated, candidate costs, search and confirmation receipts. Minimality is limited to the supplied search-qualified alternatives; confirmed is conditional on the mathematical duration model, not real-world delivery reliability. Independently callable Rust CPU tool.","description_similarity":null,"before_hash":null,"after_hash":"f19a83f6036e1f10cb2024cf68d9cc78"},{"tool":"stress_test_observation","kind":"added","observed_at":"2026-10-01T08:47:34.143Z","fields":[],"description_before":null,"description_after":"Search 1–32 supplied hypothetical angular-bias/clock-correction perturbations for counterexamples to a declared reconstruction-stability claim. Rust fits the original observations, applies each bounded perturbation to one observer, and refits the same spherical constant-velocity model. A counterexample can violate the position-shift limit or the requirement for a usable consistent fit; solver non-convergence remains inconclusive. Return evaluated cases, native fits, first counterexample and explicit budget/refusal status. none_found applies only to examined admissible cases, never global robustness or an object-identification conclusion. No new observations or independent scientific corroboration are acquired. Explicit hypothetical acknowledgement is required. Independently callable CPU tool; an optional composition binding passes the complete validated request, never an invented observation.","description_similarity":null,"before_hash":null,"after_hash":"654096806eb6520df1df397f5ee6f39a"},{"tool":"assimilate_observation","kind":"added","observed_at":"2026-10-01T08:47:34.143Z","fields":[],"description_before":null,"description_after":"Refit original angular observations together with one explicitly supplied new angular series. Rust computes the baseline itself, uses its mean only as an initialization, and includes every original/new angular pair once without adding the baseline covariance as a prior. New timestamps are already clock-corrected and must follow the baseline; existing stations retain coordinates and angular noise. Return baseline and updated native fits plus conditional before/forecast/refit uncertainty at one common horizon, or an explicit rejection. A mean-position shift is not error against known truth; new data may contradict the model or worsen uncertainty. The caller must declare data_origin synthetic or measured; neither declaration is authenticated. No hidden truth, client baseline/covariance or forecast-only angles are generated by this tool. Independently callable Rust CPU tool.","description_similarity":null,"before_hash":null,"after_hash":"4c8c66dd47b52d122d04f8d5977459a9"},{"tool":"plan_observation","kind":"added","observed_at":"2026-10-01T08:47:34.143Z","fields":[],"description_before":null,"description_after":"Fit original angular observations in Rust, then rank 1–64 proposed observation series by predicted position uncertainty at one common corrected-time horizon. Each candidate supplies a station, 3–120 future times, angular standard deviations and a declared cost, never candidate angles or a client-supplied baseline/covariance. Existing stations use observer_1, observer_2, etc. The local linear information update assumes independent new errors, exact stations/clocks and constant velocity in spherical ECEF. Returns the real baseline fit and conditional forecasts, or baseline_rejected; predicted does not mean a new measurement was acquired or that an admissible candidate exists. Ranking is only over supplied candidates, and geometric elevation does not establish terrain visibility or sensor availability. Independently callable CPU tool; an optional composition binding passes the complete validated request, never an invented observation.","description_similarity":null,"before_hash":null,"after_hash":"1141910bffe177525182a96a78696183"}],"next_before":"256022","next_actions":[{"action":"list_changes","description":"Older changes","href":"/v1/servers/com.scorecompute%2Fscorecompute/changes?before=256022&limit=50"}]}