{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P4AZO3LS45OTHATF6F5U7JLS34","short_pith_number":"pith:P4AZO3LS","schema_version":"1.0","canonical_sha256":"7f01976d72e75d338265f17b4fa572df0ef24038f9b4efc8929736e8d0d9efa9","source":{"kind":"arxiv","id":"2411.15951","version":1},"attestation_state":"computed","paper":{"title":"Partial Identifiability and Misspecification in Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Joar Skalse","submitted_at":"2024-11-24T18:35:46Z","abstract_excerpt":"The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\\pi$. This problem is difficult, for several reasons. First of all, there are typically multiple reward functions which are compatible with a given policy; this means that the reward function is only *partially identifiable*, and that IRL contains a certain fundamental degree of ambiguity. Secondly, in order to infer $R$ from $\\pi$, an IRL algorithm must have a *behavioural model* of how $\\pi$ relates to $R$. However, the true relationship between human preferences and human behaviour is very compl"},"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":"2411.15951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-24T18:35:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"326dad65e4b2956bb30150e1f5ca74cf2696532c41edfd6eb961127312cc8393","abstract_canon_sha256":"f290e3da41d73613aeeb090c97245e83e14d69636192dda83fd6216736df12bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:01.694983Z","signature_b64":"p8i4olPyUh4RT32eAXaflT/OzLKYZdI47fQqEOUckE6VTuM4zixCeZN0UMG7ZzpgiBwdEhfPi+j4FEg7nXGFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f01976d72e75d338265f17b4fa572df0ef24038f9b4efc8929736e8d0d9efa9","last_reissued_at":"2026-07-05T09:40:01.694535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:01.694535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Partial Identifiability and Misspecification in Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Joar Skalse","submitted_at":"2024-11-24T18:35:46Z","abstract_excerpt":"The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\\pi$. This problem is difficult, for several reasons. First of all, there are typically multiple reward functions which are compatible with a given policy; this means that the reward function is only *partially identifiable*, and that IRL contains a certain fundamental degree of ambiguity. Secondly, in order to infer $R$ from $\\pi$, an IRL algorithm must have a *behavioural model* of how $\\pi$ relates to $R$. However, the true relationship between human preferences and human behaviour is very compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15951","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/2411.15951/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":"2411.15951","created_at":"2026-07-05T09:40:01.694587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15951v1","created_at":"2026-07-05T09:40:01.694587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15951","created_at":"2026-07-05T09:40:01.694587+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4AZO3LS45OT","created_at":"2026-07-05T09:40:01.694587+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4AZO3LS45OTHATF","created_at":"2026-07-05T09:40:01.694587+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4AZO3LS","created_at":"2026-07-05T09:40:01.694587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00248","citing_title":"Causal Foundations of Collective Agency","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34","json":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34.json","graph_json":"https://pith.science/api/pith-number/P4AZO3LS45OTHATF6F5U7JLS34/graph.json","events_json":"https://pith.science/api/pith-number/P4AZO3LS45OTHATF6F5U7JLS34/events.json","paper":"https://pith.science/paper/P4AZO3LS"},"agent_actions":{"view_html":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34","download_json":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34.json","view_paper":"https://pith.science/paper/P4AZO3LS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15951&json=true","fetch_graph":"https://pith.science/api/pith-number/P4AZO3LS45OTHATF6F5U7JLS34/graph.json","fetch_events":"https://pith.science/api/pith-number/P4AZO3LS45OTHATF6F5U7JLS34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/action/storage_attestation","attest_author":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/action/author_attestation","sign_citation":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/action/citation_signature","submit_replication":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/action/replication_record"}},"created_at":"2026-07-05T09:40:01.694587+00:00","updated_at":"2026-07-05T09:40:01.694587+00:00"}