{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z54RYTFEABGFK6WD2F6Z7W7JC5","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":"f5c3b28e3735b7c63a2649dc552be9bf0267af4481943e7f836a5a8fe1758a4b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-16T14:03:58Z","title_canon_sha256":"04fffbe5ca69d4e35db0406b1d7bafa4a7543d8fdfba3bf3cded295d6c0f8e90"},"schema_version":"1.0","source":{"id":"2509.13389","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.13389","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2509.13389v7","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.13389","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z54RYTFEABGF","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z54RYTFEABGFK6WD","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z54RYTFE","created_at":"2026-05-26T02:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:140fe09cabaa3ba7b4e09a0fb0760fee18b0e9005da744e976ee646128f13386","target":"graph","created_at":"2026-05-26T02:05:02Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Both the STRIPS Transformer and a standard transformer with stick-breaking attention can be used to produce models that support planning with off-the-shelf STRIPS planners over exponentially many unseen initial states and goals."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The learned next-token models are sufficiently accurate and complete to serve as drop-in STRIPS action models for arbitrary unseen states and goals, with correctness evaluated exactly in the symbolic setting (abstract, evaluation section implied by results on generalization and planning performance)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Transformers trained via next-token prediction on action traces can learn STRIPS action models that support planning over exponentially many unseen initial states and goals."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Next-token prediction on action traces yields STRIPS world models accurate enough for planning on unseen states and goals."}],"snapshot_sha256":"cda8e7471192580d7771e5564c42e9ff1cc2359f7c6a8563565fc6171b18c921"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.13389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study whether next-token prediction can yield world models that truly support planning, in a controlled symbolic setting where propositional STRIPS action models are learned from action traces alone and correctness can be evaluated exactly. We introduce two architectures. The first is the STRIPS Transformer, a symbolically aligned model grounded in theoretical results linking transformers and the formal language structure of STRIPS domains. The second is a standard transformer architecture without explicit symbolic structure built in, for which we study different positional encoding schemes","authors_text":"Carlos N\\'u\\~nez-Molina, Hector Geffner, Vicen\\c{c} G\\'omez","cross_cats":[],"headline":"Next-token prediction on action traces yields STRIPS world models accurate enough for planning on unseen states and goals.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-16T14:03:58Z","title":"From Next Token Prediction to (STRIPS) World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.13389","kind":"arxiv","version":7},"verdict":{"created_at":"2026-05-18T16:17:00.156670Z","id":"4bac0768-2c65-4d4a-8ffc-84b0840420c2","model_set":{"reader":"grok-4.3"},"one_line_summary":"Transformers trained via next-token prediction on action traces can learn STRIPS action models that support planning over exponentially many unseen initial states and goals.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Next-token prediction on action traces yields STRIPS world models accurate enough for planning on unseen states and goals.","strongest_claim":"Both the STRIPS Transformer and a standard transformer with stick-breaking attention can be used to produce models that support planning with off-the-shelf STRIPS planners over exponentially many unseen initial states and goals.","weakest_assumption":"The learned next-token models are sufficiently accurate and complete to serve as drop-in STRIPS action models for arbitrary unseen states and goals, with correctness evaluated exactly in the symbolic setting (abstract, evaluation section implied by results on generalization and planning performance)."}},"verdict_id":"4bac0768-2c65-4d4a-8ffc-84b0840420c2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1ff7d86a8e63cb52ebd245e06fca5273fb396fd2ed72810195704880f46e9029","target":"record","created_at":"2026-05-26T02:05:02Z","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":"f5c3b28e3735b7c63a2649dc552be9bf0267af4481943e7f836a5a8fe1758a4b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-16T14:03:58Z","title_canon_sha256":"04fffbe5ca69d4e35db0406b1d7bafa4a7543d8fdfba3bf3cded295d6c0f8e90"},"schema_version":"1.0","source":{"id":"2509.13389","kind":"arxiv","version":7}},"canonical_sha256":"cf791c4ca4004c557ac3d17d9fdbe917643c867d8fed2eb7b2e50905b5cd78cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf791c4ca4004c557ac3d17d9fdbe917643c867d8fed2eb7b2e50905b5cd78cc","first_computed_at":"2026-05-26T02:05:02.079507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:02.079507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t+Ejxy5uieDMpYdkjh1Fu5voLPRGoHWbNsu6yQ+VnQz46QVkbuJ04k9bC0LhWoYec5VCV6axWMBe/V4NN3xOBQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:02.080457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.13389","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ff7d86a8e63cb52ebd245e06fca5273fb396fd2ed72810195704880f46e9029","sha256:140fe09cabaa3ba7b4e09a0fb0760fee18b0e9005da744e976ee646128f13386"],"state_sha256":"8eb70029d41c861452c71eb231c09f0033b0d0eb1753ad483fe97b7ef4364d3f"}