{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UICXWBFKVOGCTVSSQ3ROGKPKGP","short_pith_number":"pith:UICXWBFK","canonical_record":{"source":{"id":"2607.14169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T08:54:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a65db1efaf78b4f65aef1e6a40c322761c07efeac4adca24ba5b0d8718563466","abstract_canon_sha256":"e22c72aca18b8e93f8e27ec11f7b3fa21f10dc4dd9cd22ba72801b2d9bc23394"},"schema_version":"1.0"},"canonical_sha256":"a2057b04aaab8c29d65286e2e329ea33ef5fea9df35657fe71f215d8732a67f2","source":{"kind":"arxiv","id":"2607.14169","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14169","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14169v1","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14169","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"UICXWBFKVOGC","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"UICXWBFKVOGCTVSS","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"UICXWBFK","created_at":"2026-07-17T00:20:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UICXWBFKVOGCTVSSQ3ROGKPKGP","target":"record","payload":{"canonical_record":{"source":{"id":"2607.14169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T08:54:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a65db1efaf78b4f65aef1e6a40c322761c07efeac4adca24ba5b0d8718563466","abstract_canon_sha256":"e22c72aca18b8e93f8e27ec11f7b3fa21f10dc4dd9cd22ba72801b2d9bc23394"},"schema_version":"1.0"},"canonical_sha256":"a2057b04aaab8c29d65286e2e329ea33ef5fea9df35657fe71f215d8732a67f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:20:54.971899Z","signature_b64":"GbPndv2w55fR9YBO6UX9hL5twkGVUW7g/CaKKonVP64cW4TlTx0lj9UaqcfDjcIJqu05kwRTP10xwN6yjPtECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2057b04aaab8c29d65286e2e329ea33ef5fea9df35657fe71f215d8732a67f2","last_reissued_at":"2026-07-17T00:20:54.971045Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:20:54.971045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.14169","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T00:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9J/Y7cDwdfrZ6It1NeSVwIAjPY413v5/9x6x0q7ybbdY85ac3zsolCXX7cjPZTpaWJp8ObZ+3wdeEQkesEkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:18:44.845013Z"},"content_sha256":"192c4e19386e3a28a48bd46339956661e2b8f0d7d08ce080a193bbe450b7ae14","schema_version":"1.0","event_id":"sha256:192c4e19386e3a28a48bd46339956661e2b8f0d7d08ce080a193bbe450b7ae14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UICXWBFKVOGCTVSSQ3ROGKPKGP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Javier Aguilar Mart\\'in","submitted_at":"2026-07-15T08:54:59Z","abstract_excerpt":"Large language models can synthesize a game's rules as executable code - a Code World Model (CWM) - which a classical planner then searches over. Such models are typically accepted when they reach high transition accuracy on sampled trajectories. We argue this is the wrong notion of adequacy for planning.\n  We show four things. (1) An LLM-synthesized CWM can pass a sampling gate at 100% transition accuracy and be $\\geq 98\\%$ state-accurate on the planner's own search distribution, yet lose systematically at play, because the $<1\\%$ it gets wrong is exactly the pivotal dynamics; the play cost o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14169","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.14169/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T00:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GqS2porcjKLHYqyRi3JmULTdgVw6At7fiS/H0uzi4w0gAcFiFausMLpYEEFoFtzpKiPDz8eUFweAWXvD44WIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:18:44.845527Z"},"content_sha256":"a969e4f5a9a39f86793e58470ce4e5c0c56034b110799b13eb2d27679d762f39","schema_version":"1.0","event_id":"sha256:a969e4f5a9a39f86793e58470ce4e5c0c56034b110799b13eb2d27679d762f39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UICXWBFKVOGCTVSSQ3ROGKPKGP/bundle.json","state_url":"https://pith.science/pith/UICXWBFKVOGCTVSSQ3ROGKPKGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UICXWBFKVOGCTVSSQ3ROGKPKGP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T18:18:44Z","links":{"resolver":"https://pith.science/pith/UICXWBFKVOGCTVSSQ3ROGKPKGP","bundle":"https://pith.science/pith/UICXWBFKVOGCTVSSQ3ROGKPKGP/bundle.json","state":"https://pith.science/pith/UICXWBFKVOGCTVSSQ3ROGKPKGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UICXWBFKVOGCTVSSQ3ROGKPKGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UICXWBFKVOGCTVSSQ3ROGKPKGP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e22c72aca18b8e93f8e27ec11f7b3fa21f10dc4dd9cd22ba72801b2d9bc23394","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T08:54:59Z","title_canon_sha256":"a65db1efaf78b4f65aef1e6a40c322761c07efeac4adca24ba5b0d8718563466"},"schema_version":"1.0","source":{"id":"2607.14169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14169","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14169v1","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14169","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"UICXWBFKVOGC","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"UICXWBFKVOGCTVSS","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"UICXWBFK","created_at":"2026-07-17T00:20:54Z"}],"graph_snapshots":[{"event_id":"sha256:a969e4f5a9a39f86793e58470ce4e5c0c56034b110799b13eb2d27679d762f39","target":"graph","created_at":"2026-07-17T00:20:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.14169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models can synthesize a game's rules as executable code - a Code World Model (CWM) - which a classical planner then searches over. Such models are typically accepted when they reach high transition accuracy on sampled trajectories. We argue this is the wrong notion of adequacy for planning.\n  We show four things. (1) An LLM-synthesized CWM can pass a sampling gate at 100% transition accuracy and be $\\geq 98\\%$ state-accurate on the planner's own search distribution, yet lose systematically at play, because the $<1\\%$ it gets wrong is exactly the pivotal dynamics; the play cost o","authors_text":"Javier Aguilar Mart\\'in","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T08:54:59Z","title":"When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14169","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:192c4e19386e3a28a48bd46339956661e2b8f0d7d08ce080a193bbe450b7ae14","target":"record","created_at":"2026-07-17T00:20:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e22c72aca18b8e93f8e27ec11f7b3fa21f10dc4dd9cd22ba72801b2d9bc23394","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T08:54:59Z","title_canon_sha256":"a65db1efaf78b4f65aef1e6a40c322761c07efeac4adca24ba5b0d8718563466"},"schema_version":"1.0","source":{"id":"2607.14169","kind":"arxiv","version":1}},"canonical_sha256":"a2057b04aaab8c29d65286e2e329ea33ef5fea9df35657fe71f215d8732a67f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2057b04aaab8c29d65286e2e329ea33ef5fea9df35657fe71f215d8732a67f2","first_computed_at":"2026-07-17T00:20:54.971045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:20:54.971045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GbPndv2w55fR9YBO6UX9hL5twkGVUW7g/CaKKonVP64cW4TlTx0lj9UaqcfDjcIJqu05kwRTP10xwN6yjPtECg==","signature_status":"signed_v1","signed_at":"2026-07-17T00:20:54.971899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:192c4e19386e3a28a48bd46339956661e2b8f0d7d08ce080a193bbe450b7ae14","sha256:a969e4f5a9a39f86793e58470ce4e5c0c56034b110799b13eb2d27679d762f39"],"state_sha256":"1ca51dd9751600141495cf6545c2e9ce4443ff5656a95206a063f6a382426459"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tcAyqF32ANw7oYc3NCmrPvUlyfJacp1QLZgGtUtpiNZtHF+XvVBkZ92xNJhZmPMf/qgoLusldJ3rIM23UKzkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:18:44.850458Z","bundle_sha256":"1068bbdf01a4e52d4f7ceb85dc7bd287c71b1d2eb7f5cd5f7de1bbe088e841e1"}}