{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P4AZO3LS45OTHATF6F5U7JLS34","short_pith_number":"pith:P4AZO3LS","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"},"canonical_sha256":"7f01976d72e75d338265f17b4fa572df0ef24038f9b4efc8929736e8d0d9efa9","source":{"kind":"arxiv","id":"2411.15951","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15951","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15951v1","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15951","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"P4AZO3LS45OT","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"P4AZO3LS45OTHATF","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"P4AZO3LS","created_at":"2026-07-05T09:40:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P4AZO3LS45OTHATF6F5U7JLS34","target":"record","payload":{"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"},"canonical_sha256":"7f01976d72e75d338265f17b4fa572df0ef24038f9b4efc8929736e8d0d9efa9","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"},"source_kind":"arxiv","source_id":"2411.15951","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":"2026-07-05T09:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IuWdQVDWLZjltYY8MqGwFGwym2fFiTd1nx9Gxka04lLvzVUcliQj14EW3HLjDz/ssT+uQSAdURnIaXnUfs1/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:32:01.225035Z"},"content_sha256":"4c820cb680ab294b8ab37488ceb1e3e3bc1eb2b0e8bcba4a89230fb22032ab60","schema_version":"1.0","event_id":"sha256:4c820cb680ab294b8ab37488ceb1e3e3bc1eb2b0e8bcba4a89230fb22032ab60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P4AZO3LS45OTHATF6F5U7JLS34","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2AhkHy5qbY+xbsqjNR3hKSD1WY6onJHfy7lSbrCuDosPPY/Tmttveikw7hSjobC3HHCJmbagBwoBasXItkLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:32:01.225971Z"},"content_sha256":"95f942b52c4dd8d6fb2ae87c9c5540a89aba22cab05079ef03b407d57fab75a9","schema_version":"1.0","event_id":"sha256:95f942b52c4dd8d6fb2ae87c9c5540a89aba22cab05079ef03b407d57fab75a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/bundle.json","state_url":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4AZO3LS45OTHATF6F5U7JLS34/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":"2026-08-13T01:32:01Z","links":{"resolver":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34","bundle":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/bundle.json","state":"https://pith.science/pith/P4AZO3LS45OTHATF6F5U7JLS34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4AZO3LS45OTHATF6F5U7JLS34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P4AZO3LS45OTHATF6F5U7JLS34","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":"f290e3da41d73613aeeb090c97245e83e14d69636192dda83fd6216736df12bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-24T18:35:46Z","title_canon_sha256":"326dad65e4b2956bb30150e1f5ca74cf2696532c41edfd6eb961127312cc8393"},"schema_version":"1.0","source":{"id":"2411.15951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15951","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15951v1","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15951","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"P4AZO3LS45OT","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"P4AZO3LS45OTHATF","created_at":"2026-07-05T09:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"P4AZO3LS","created_at":"2026-07-05T09:40:01Z"}],"graph_snapshots":[{"event_id":"sha256:95f942b52c4dd8d6fb2ae87c9c5540a89aba22cab05079ef03b407d57fab75a9","target":"graph","created_at":"2026-07-05T09:40:01Z","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/2411.15951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alessandro Abate, Joar Skalse","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-24T18:35:46Z","title":"Partial Identifiability and Misspecification in Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15951","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":"sha256:4c820cb680ab294b8ab37488ceb1e3e3bc1eb2b0e8bcba4a89230fb22032ab60","target":"record","created_at":"2026-07-05T09:40:01Z","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":"f290e3da41d73613aeeb090c97245e83e14d69636192dda83fd6216736df12bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-24T18:35:46Z","title_canon_sha256":"326dad65e4b2956bb30150e1f5ca74cf2696532c41edfd6eb961127312cc8393"},"schema_version":"1.0","source":{"id":"2411.15951","kind":"arxiv","version":1}},"canonical_sha256":"7f01976d72e75d338265f17b4fa572df0ef24038f9b4efc8929736e8d0d9efa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f01976d72e75d338265f17b4fa572df0ef24038f9b4efc8929736e8d0d9efa9","first_computed_at":"2026-07-05T09:40:01.694535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:01.694535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p8i4olPyUh4RT32eAXaflT/OzLKYZdI47fQqEOUckE6VTuM4zixCeZN0UMG7ZzpgiBwdEhfPi+j4FEg7nXGFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:01.694983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c820cb680ab294b8ab37488ceb1e3e3bc1eb2b0e8bcba4a89230fb22032ab60","sha256:95f942b52c4dd8d6fb2ae87c9c5540a89aba22cab05079ef03b407d57fab75a9"],"state_sha256":"fe10143be494eac5e914238bee1403f9aba602511a5b253dd31605b44fffaccf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"luIOhUicKrUyAyy9Lu0GFY/9w+XYbwmky9a9kCj6VwA6NmXOKT3ITMle/cIT+Y3DpvoUhFRtLMJqXSHaOvzbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:32:01.231695Z","bundle_sha256":"770f8d6984df0736cd41978e909d07ab8dcc9a2782dfc96f527387a273f8a9c1"}}