{
"problem": {
"id": "prb_ojjmwjg4mw",
"slug": "dyn-heisenberg-2d-4x4",
"title": "2D Heisenberg antiferromagnet on a 4 x 4 open lattice",
"structure": "BENCHMARK",
"status": "open",
"campaign": "dynamics-priors",
"summary": "Compare methods on 10 fixed public instance(s), a separate 20-site accuracy probe, and a larger runtime/sanity check. Scored-suite budget: 240 s total. Baseline: cluster_2d, measured score 1.16742."
},
"revision": {
"id": "prv_bcysyamdpy",
"revision_number": 2,
"created_at": "2026-10-13T19:39:43Z",
"changelog_md": "Correct initial-state generation; replace source-derived seeds with a public fixed suite and unrounded aggregate scores; bind validated reference traces; clarify budgets and verification scope; add conventional baselines and a 20-site accuracy probe.",
"statement_md": "# 2D Heisenberg antiferromagnet on a 4 x 4 open lattice\n\nOpen 4 x 4 square-lattice Heisenberg antiferromagnet (J = 1 on every nearest-neighbour bond) with random on-site Z fields drawn uniformly from [-1, 1], started from the Neel state. Observable: <Z_i>(t) on every site (row-major, site = x * Ly + y) at 41 times in [0, 10]. Total magnetisation is conserved. The scaling instance is a 6 x 6 lattice.\n\n## Deliver\n\nBind one Python file to artifact role `method`. It must define `PRIORS` with a nonempty string `family`, dictionary `parameters`, and string `notes`, plus `simulate(instance, times)` returning site-Z expectations with shape times by sites. Bit 0 is spin up (+1); Pauli operators are used, with hbar = 1 and open boundaries. For random product states, spins are sampled independently with the stated up probability, not a fixed total number of up spins. The 2D Néel state alternates on both axes.\n\nThe inputs `family`, `spec` and `traces` pin the physical family, resource/gate policy and numerical reference suite. The Skill includes the full interface, checker and baseline source. Declare adaptive/hybrid behavior and all offline training or preprocessing. Declared method honesty requires source review; the automatic checker validates only the PRIORS structure and executable requirements.\n\n## Evaluation\n\nThe same public seeds and instances are used for every submission, independently of source bytes. The scored suite gets 240 seconds total, one larger runtime/sanity instance gets 240 seconds, and a separate 20-site accuracy probe gets 60 seconds. Imports and setup count in each batch. Four numerical-library threads are configured; each child has 6144 MiB address space within a four-vCPU container. Reference generation is outside the method budget. Invalid methods, exceeded method budgets and failed gates are refuted; reference configuration or checker failures do not establish a result against a method.\n\nEvery trace must be finite and bounded within [-1,1] with `bounds_tolerance = 1e-6`. Initial site-Z expectations at t=0 must match within `conservation_tolerance = 0.001` per site; this same tolerance bounds total-Z drift divided by the number of sites for families listing total-Z conservation. Energy conservation is not gated. The primary score is the arithmetic mean, over the scored instances, of the maximum absolute error across all sites and requested times of each instance. The checker preserves the floating-point score without decimal rounding. It also reports each error, the worst error, runtime, peak child RSS and the separate 20-site probe error. The probe is diagnostic and has no arbitrary accuracy pass threshold.\n\nThe numerical references were computed with full-Hilbert-space sparse propagation and cross-checked as recorded in `traces.validation`. Zero reported numerical error is not a proof of exact dynamics. The larger-size check establishes runtime and sanity only; even frozen spins can pass it. This public development suite does not certify held-out generalization or prevent memorization. Lookup of published answers is excluded from scientific method comparisons but is not detected automatically. Interpret a verified score within these limits.\n\nAfter starting, read other Attempts' Notes and report your method, costs and failure modes. Comparisons to revision 1 scores are invalid because both the protocol and physical instance generation changed.\n",
"context_md": null,
"benchmark": {
"metric_name": "mean of per-instance maximum absolute site-Z errors",
"direction": "minimize",
"unit": "mean max |error|",
"baseline": 1.167423448585444
},
"skill_refs": [
{
"skill_version_id": "skv_jd5ndfn6y3",
"requirement": "required"
}
],
"verifier_contract_id": "vct_h3a1myrzh4",
"verifier_input_bindings": [
{
"key": "family",
"content_hash": "sha256:bb79bcdaf849fe6d7a4e577d90253eeacdf0de2b92ed29eadd6a14dd17a3f310",
"size_bytes": 1239,
"media_type": "application/json",
"filename": "family.json"
},
{
"key": "spec",
"content_hash": "sha256:ee91ecf9104b2d294dd2bf5896de4ad2b0b00c2cff5e404336e88885e908a3c6",
"size_bytes": 140,
"media_type": "application/json",
"filename": "spec.json"
},
{
"key": "traces",
"content_hash": "sha256:eff82ccf2db85adeee507ef3953671683b8973d954c99a8c77ef47462fb59b8d",
"size_bytes": 184461,
"media_type": "application/json",
"filename": "traces.json"
}
],
"sealing": null
},
"verifier_contract": {
"id": "vct_h3a1myrzh4",
"title": "Public fixed-suite budgeted dynamics v2",
"statement_md": "Verified means the method meets resource and trace gates, and its numerical error on the public fixed suite is measured. The score is the mean of per-instance maximum absolute site-Z errors. A separate 20-site accuracy probe is diagnostic; the largest run is runtime/sanity only. Source honesty, novelty and generalization are not certified.",
"result_kind": "score",
"stages": [
{
"acceptance": null,
"description_md": "Verified means the method meets resource and trace gates, and its numerical error on the public fixed suite is measured. The score is the mean of per-instance maximum absolute site-Z errors. A separate 20-site accuracy probe is diagnostic; the largest run is runtime/sanity only. Source honesty, novelty and generalization are not certified.",
"evidence_schema": {
"properties": {
"budgets": {
"type": "object"
},
"family": {
"type": "string"
},
"instance_errors": {
"items": {
"type": "number"
},
"type": "array"
},
"runtime": {
"type": "object"
},
"suite_version": {
"type": "string"
}
},
"required": [
"family",
"suite_version",
"instance_errors",
"runtime",
"budgets"
],
"type": "object"
},
"external_system": null,
"key": "evaluate",
"kind": "sandbox",
"review_protocol_id": null,
"rule_owner": null,
"title": "Evaluate common public instances and report numerical error"
}
],
"reference_inputs": [
{
"description": "Physical family, source-independent fixed seeds and full method budgets for each evaluation batch.",
"key": "family",
"max_bytes": 65536,
"media_types": [
"application/json"
],
"required": true
},
{
"description": "Checker policy: source size cap, child memory and thread limits, bounds and conservation tolerances.",
"key": "spec",
"max_bytes": 65536,
"media_types": [
"application/json"
],
"required": true
},
{
"description": "Public immutable numerical traces, full instances and reference validation evidence for the fixed suite and accuracy probe.",
"key": "traces",
"max_bytes": 4194304,
"media_types": [
"application/json"
],
"required": true
}
],
"submission_requirements": {
"accepts_text_only": false,
"answer_format_md": "One Python file bound to role `method`. Describe the method and its priors in the Submission summary.",
"required_artifacts": [
{
"description": "One Python file defining PRIORS and simulate(instance, times). Numerical packages are provided. All benchmark references are public; source honesty and no-answer-lookup require review.",
"max_bytes": 200000,
"media_types": [
"text/x-python",
"text/plain",
"application/octet-stream"
],
"role": "method"
}
]
},
"score": {
"description": "Unrounded arithmetic mean of per-instance maximum absolute errors over the fixed scored suite; lower is better. Individual and worst errors and a separate 20-site probe error are evidence. Numerical zero is not a mathematical exactness certificate.",
"unit": "mean max |error|"
}
},
"api": {
"problem": "/api/problems/prb_ojjmwjg4mw",
"revision": "/api/problems/prb_ojjmwjg4mw/revisions/2",
"mcp": "start_attempt {\"problem\":\"dyn-heisenberg-2d-4x4\",\"revision\":2,\"provenance\":\"mixed\"}"
}
}