{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XLN36F6LMHJFLPDIIRG552K5WQ","short_pith_number":"pith:XLN36F6L","schema_version":"1.0","canonical_sha256":"badbbf17cb61d255bc68444ddee95db40a493a41620837fccff5118aa40a4ca6","source":{"kind":"arxiv","id":"2501.12633","version":3},"attestation_state":"computed","paper":{"title":"Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anqi Wu, Feiyang Wu, Jeffrey Markowitz, Jingyang Ke, Jiyi Wang","submitted_at":"2025-01-22T04:38:33Z","abstract_excerpt":"Traditional approaches to studying decision-making in neuroscience focus on simplified behavioral tasks where animals perform repetitive, stereotyped actions to receive explicit rewards. While informative, these methods constrain our understanding of decision-making to short timescale behaviors driven by explicit goals. In natural environments, animals exhibit more complex, long-term behaviors driven by intrinsic motivations that are often unobservable. Recent works in time-varying inverse reinforcement learning (IRL) aim to capture shifting motivations in long-term, freely moving behaviors. H"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.12633","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T04:38:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"923539743db2f12c12db5932fd2c9f2d0a0bf2fbcefbef2e3127db00108dc443","abstract_canon_sha256":"1fd61fff4dd01d4d2f03ca28c0f02341abd30589221d52a22b528f76ce6c5c41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:15.097071Z","signature_b64":"3K7P4WbRSz/GEGvSM9RsIzheBlxeWt1TK83Ri+bg2u379Y9/kV7psb7UXDUjptts9stxtUbtbdD52eAN7sHwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"badbbf17cb61d255bc68444ddee95db40a493a41620837fccff5118aa40a4ca6","last_reissued_at":"2026-07-05T11:37:15.096522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:15.096522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anqi Wu, Feiyang Wu, Jeffrey Markowitz, Jingyang Ke, Jiyi Wang","submitted_at":"2025-01-22T04:38:33Z","abstract_excerpt":"Traditional approaches to studying decision-making in neuroscience focus on simplified behavioral tasks where animals perform repetitive, stereotyped actions to receive explicit rewards. While informative, these methods constrain our understanding of decision-making to short timescale behaviors driven by explicit goals. In natural environments, animals exhibit more complex, long-term behaviors driven by intrinsic motivations that are often unobservable. Recent works in time-varying inverse reinforcement learning (IRL) aim to capture shifting motivations in long-term, freely moving behaviors. H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12633","kind":"arxiv","version":3},"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/2501.12633/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.12633","created_at":"2026-07-05T11:37:15.096590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12633v3","created_at":"2026-07-05T11:37:15.096590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12633","created_at":"2026-07-05T11:37:15.096590+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLN36F6LMHJF","created_at":"2026-07-05T11:37:15.096590+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLN36F6LMHJFLPDI","created_at":"2026-07-05T11:37:15.096590+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLN36F6L","created_at":"2026-07-05T11:37:15.096590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26998","citing_title":"Probabilistic Recurrent Intention Switching Model","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25496","citing_title":"Improving Zero-Shot Offline RL via Behavioral Task Sampling","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ","json":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ.json","graph_json":"https://pith.science/api/pith-number/XLN36F6LMHJFLPDIIRG552K5WQ/graph.json","events_json":"https://pith.science/api/pith-number/XLN36F6LMHJFLPDIIRG552K5WQ/events.json","paper":"https://pith.science/paper/XLN36F6L"},"agent_actions":{"view_html":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ","download_json":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ.json","view_paper":"https://pith.science/paper/XLN36F6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12633&json=true","fetch_graph":"https://pith.science/api/pith-number/XLN36F6LMHJFLPDIIRG552K5WQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XLN36F6LMHJFLPDIIRG552K5WQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ/action/storage_attestation","attest_author":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ/action/author_attestation","sign_citation":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ/action/citation_signature","submit_replication":"https://pith.science/pith/XLN36F6LMHJFLPDIIRG552K5WQ/action/replication_record"}},"created_at":"2026-07-05T11:37:15.096590+00:00","updated_at":"2026-07-05T11:37:15.096590+00:00"}