{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4YE7E5IJQTFMFUIDZVKKAWUMNZ","short_pith_number":"pith:4YE7E5IJ","canonical_record":{"source":{"id":"2312.00054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-29T00:09:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cf58d181bf7e0ec40ba380a1513feb303b1f5c3e9de1d830cd887e0ba63ba178","abstract_canon_sha256":"e55f509fb9b56994c0270a1130cd4171bc8a3c6d46a8781b99ee40a0b3701488"},"schema_version":"1.0"},"canonical_sha256":"e609f2750984cac2d103cd54a05a8c6e61720a24e1c164526ef046a9a5628424","source":{"kind":"arxiv","id":"2312.00054","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00054","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00054v2","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00054","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"pith_short_12","alias_value":"4YE7E5IJQTFM","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"pith_short_16","alias_value":"4YE7E5IJQTFMFUID","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"pith_short_8","alias_value":"4YE7E5IJ","created_at":"2026-07-05T07:43:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4YE7E5IJQTFMFUIDZVKKAWUMNZ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.00054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-29T00:09:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cf58d181bf7e0ec40ba380a1513feb303b1f5c3e9de1d830cd887e0ba63ba178","abstract_canon_sha256":"e55f509fb9b56994c0270a1130cd4171bc8a3c6d46a8781b99ee40a0b3701488"},"schema_version":"1.0"},"canonical_sha256":"e609f2750984cac2d103cd54a05a8c6e61720a24e1c164526ef046a9a5628424","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:34.301656Z","signature_b64":"wMpzAx1r38V+L0f/S/vEdnX1JxQJQ3SbUfNoniMu6mRrBX90RZ1cvOwZ+611oOz4TirIIB+5i+st7wAG/9K2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e609f2750984cac2d103cd54a05a8c6e61720a24e1c164526ef046a9a5628424","last_reissued_at":"2026-07-05T07:43:34.301133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:34.301133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.00054","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:43:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sq4QCIbfBYEdqTjk7ZEzKBS/afHfzFo/gb4AdOMe/AA4+IT8VLmuw3sAnJxtEbJ1eke9kr5SkGteztCJbKlvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:15:49.666859Z"},"content_sha256":"54e8e1cf34f1aa2e2fe47e1e6d6d248eb4ac62db94838d8ae28f8d9af96b350b","schema_version":"1.0","event_id":"sha256:54e8e1cf34f1aa2e2fe47e1e6d6d248eb4ac62db94838d8ae28f8d9af96b350b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4YE7E5IJQTFMFUIDZVKKAWUMNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Lei Zhao, Mengdi Wang, Yu Bai","submitted_at":"2023-11-29T00:09:01Z","abstract_excerpt":"Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an \\emph{expert policy} -- plays a critical role in developing intelligent systems. While widely used in applications, theoretical understandings of IRL present unique challenges and remain less developed compared with standard RL. For example, it remains open how to do IRL efficiently in standard \\emph{offline} settings with pre-collected data, where states are obtained from a \\emph{behavior policy} (which could be the expert policy itself), and actions are sampled from the expert policy.\n "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00054","kind":"arxiv","version":2},"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/2312.00054/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":"2026-07-05T07:43:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VWGAfP62ekBCggqWctUJsM7SXyV6Z7Q6NRhtJ2CIAEpvyjnKDSQ0BhCrxiqppzyA7CeHd5Z99yz6/AIgeAuiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:15:49.667556Z"},"content_sha256":"4409b4ddf9adbe38251ccc0f00b8beaddc397a1c2caa7f512124894ea9326764","schema_version":"1.0","event_id":"sha256:4409b4ddf9adbe38251ccc0f00b8beaddc397a1c2caa7f512124894ea9326764"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YE7E5IJQTFMFUIDZVKKAWUMNZ/bundle.json","state_url":"https://pith.science/pith/4YE7E5IJQTFMFUIDZVKKAWUMNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YE7E5IJQTFMFUIDZVKKAWUMNZ/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":"2026-08-08T01:15:49Z","links":{"resolver":"https://pith.science/pith/4YE7E5IJQTFMFUIDZVKKAWUMNZ","bundle":"https://pith.science/pith/4YE7E5IJQTFMFUIDZVKKAWUMNZ/bundle.json","state":"https://pith.science/pith/4YE7E5IJQTFMFUIDZVKKAWUMNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YE7E5IJQTFMFUIDZVKKAWUMNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4YE7E5IJQTFMFUIDZVKKAWUMNZ","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":"e55f509fb9b56994c0270a1130cd4171bc8a3c6d46a8781b99ee40a0b3701488","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-29T00:09:01Z","title_canon_sha256":"cf58d181bf7e0ec40ba380a1513feb303b1f5c3e9de1d830cd887e0ba63ba178"},"schema_version":"1.0","source":{"id":"2312.00054","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00054","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00054v2","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00054","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"pith_short_12","alias_value":"4YE7E5IJQTFM","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"pith_short_16","alias_value":"4YE7E5IJQTFMFUID","created_at":"2026-07-05T07:43:34Z"},{"alias_kind":"pith_short_8","alias_value":"4YE7E5IJ","created_at":"2026-07-05T07:43:34Z"}],"graph_snapshots":[{"event_id":"sha256:4409b4ddf9adbe38251ccc0f00b8beaddc397a1c2caa7f512124894ea9326764","target":"graph","created_at":"2026-07-05T07:43:34Z","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/2312.00054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an \\emph{expert policy} -- plays a critical role in developing intelligent systems. While widely used in applications, theoretical understandings of IRL present unique challenges and remain less developed compared with standard RL. For example, it remains open how to do IRL efficiently in standard \\emph{offline} settings with pre-collected data, where states are obtained from a \\emph{behavior policy} (which could be the expert policy itself), and actions are sampled from the expert policy.\n ","authors_text":"Lei Zhao, Mengdi Wang, Yu Bai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-29T00:09:01Z","title":"Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00054","kind":"arxiv","version":2},"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":"sha256:54e8e1cf34f1aa2e2fe47e1e6d6d248eb4ac62db94838d8ae28f8d9af96b350b","target":"record","created_at":"2026-07-05T07:43:34Z","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":"e55f509fb9b56994c0270a1130cd4171bc8a3c6d46a8781b99ee40a0b3701488","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-29T00:09:01Z","title_canon_sha256":"cf58d181bf7e0ec40ba380a1513feb303b1f5c3e9de1d830cd887e0ba63ba178"},"schema_version":"1.0","source":{"id":"2312.00054","kind":"arxiv","version":2}},"canonical_sha256":"e609f2750984cac2d103cd54a05a8c6e61720a24e1c164526ef046a9a5628424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e609f2750984cac2d103cd54a05a8c6e61720a24e1c164526ef046a9a5628424","first_computed_at":"2026-07-05T07:43:34.301133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:34.301133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wMpzAx1r38V+L0f/S/vEdnX1JxQJQ3SbUfNoniMu6mRrBX90RZ1cvOwZ+611oOz4TirIIB+5i+st7wAG/9K2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:34.301656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.00054","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54e8e1cf34f1aa2e2fe47e1e6d6d248eb4ac62db94838d8ae28f8d9af96b350b","sha256:4409b4ddf9adbe38251ccc0f00b8beaddc397a1c2caa7f512124894ea9326764"],"state_sha256":"060a9c760642dc08ac52b01a45192580fbac910e14ac7bf1ca3ae5bcae396d3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xufOdmtLI4aelxqFpRsmJLj7w/wVqrv4+rHF1x7i7gqyYAxw+W/+jkG3VhTtx5bt0r1eqSFrTKlGANlJYULTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:15:49.671032Z","bundle_sha256":"69366c71b2f433ef44914899eeee6cbf53c2d8b050893ec7bad9894c094bb9f3"}}