{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YPS6WFBMEJEHKR2VLC6VDJFFSB","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":"9853fe1665fdd4e54fc073f2f056fb63af8819da2c51472f5ad1fb5b6e27b7c7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T07:26:14Z","title_canon_sha256":"bc58b51a5c6c4f9a691198a5e2471146326acd630bf12df7f773090ffbad97d9"},"schema_version":"1.0","source":{"id":"2606.21173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21173","created_at":"2026-06-23T01:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21173v1","created_at":"2026-06-23T01:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21173","created_at":"2026-06-23T01:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"YPS6WFBMEJEH","created_at":"2026-06-23T01:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"YPS6WFBMEJEHKR2V","created_at":"2026-06-23T01:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"YPS6WFBM","created_at":"2026-06-23T01:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:4e32ad251e9d9432df454d100efbc74e4611b6e45b12af757e7130e0a06d0b69","target":"graph","created_at":"2026-06-23T01:12:32Z","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/2606.21173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based and model-free reinforcement learning are traditionally viewed as separate paradigms: instead of learning a model of the transition kernel $P$, model-free agents typically estimate value functions tied to a specific policy and reward. In this paper, we challenge this dichotomy by proving that value-based agents trained on a sufficiently rich set of reward functions, e.g. using goal-conditioned RL, implicitly encode a unique and accurate world model. To extract this model in practice, we introduce \\textit{$P$-learning}, an inverse analogue to $Q$-learning that samples from an agent'","authors_text":"Alexander D. Goldie, Alistair Letcher, Jakob N. Foerster, Jonathan Richens, Mattie Fellows, Oliver Richardson","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T07:26:14Z","title":"Inverting the Bellman Equation: From $Q$-Values to World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21173","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":"sha256:868ac33b754c3ecf63a35aaebb1abc6f3524de149b0605891319865574265c13","target":"record","created_at":"2026-06-23T01:12:32Z","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":"9853fe1665fdd4e54fc073f2f056fb63af8819da2c51472f5ad1fb5b6e27b7c7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T07:26:14Z","title_canon_sha256":"bc58b51a5c6c4f9a691198a5e2471146326acd630bf12df7f773090ffbad97d9"},"schema_version":"1.0","source":{"id":"2606.21173","kind":"arxiv","version":1}},"canonical_sha256":"c3e5eb142c224875475558bd51a4a59052164e3c3ee226b3f042182e9b68daca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3e5eb142c224875475558bd51a4a59052164e3c3ee226b3f042182e9b68daca","first_computed_at":"2026-06-23T01:12:32.403498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:32.403498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fWtFP8Yoz8WSD/aqLn30ne8VEzqoVtIyxtyme7rxvmQtBIaJeyKwHRFnwAnnMC75oJ1Zwr7et+y2CyaPYYKtDg==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:32.403965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:868ac33b754c3ecf63a35aaebb1abc6f3524de149b0605891319865574265c13","sha256:4e32ad251e9d9432df454d100efbc74e4611b6e45b12af757e7130e0a06d0b69"],"state_sha256":"08877f6a33418bd6a7a64dea04576089cd32cb2708e60514ed0fef03b5885372"}