{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SYA4FFT2WRXPLCVZ2DRQDA2QMG","short_pith_number":"pith:SYA4FFT2","canonical_record":{"source":{"id":"1805.12573","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T17:29:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"387c0fc64456f9a8223a00b6533643277731687efed84a6203be132fed7a1d6e","abstract_canon_sha256":"8be6d1e522f71ad4ff5110ed097259b885fb8bad16726d3893fd8deaf85178e4"},"schema_version":"1.0"},"canonical_sha256":"9601c2967ab46ef58ab9d0e301835061a8c2136e017df8c07b121f93719ed4b9","source":{"kind":"arxiv","id":"1805.12573","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12573","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12573v5","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12573","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"pith_short_12","alias_value":"SYA4FFT2WRXP","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"pith_short_16","alias_value":"SYA4FFT2WRXPLCVZ","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"pith_short_8","alias_value":"SYA4FFT2","created_at":"2026-07-05T00:11:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SYA4FFT2WRXPLCVZ2DRQDA2QMG","target":"record","payload":{"canonical_record":{"source":{"id":"1805.12573","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T17:29:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"387c0fc64456f9a8223a00b6533643277731687efed84a6203be132fed7a1d6e","abstract_canon_sha256":"8be6d1e522f71ad4ff5110ed097259b885fb8bad16726d3893fd8deaf85178e4"},"schema_version":"1.0"},"canonical_sha256":"9601c2967ab46ef58ab9d0e301835061a8c2136e017df8c07b121f93719ed4b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:46.119347Z","signature_b64":"i3pp+gQJC27AFSsiQeu7i652aX8A+ywgBA4apT9Zu2n5jPiVHeDba+2tScmnmhbNXcZb6GY4BHruPDAsAiP1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9601c2967ab46ef58ab9d0e301835061a8c2136e017df8c07b121f93719ed4b9","last_reissued_at":"2026-07-05T00:11:46.118790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:46.118790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.12573","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:11:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QAKDE6JRFHTWn5DWUYc1Nl+kLB0kgkM32A6pL46a45xHI684lOmdM8NzhKoXvJs1sSMp6MBuT8h8msCX0VELDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:04:12.447648Z"},"content_sha256":"0d33e32d4f1ad4cdec1e687f74560302ebc79e446478414f476bb20bc5c0a659","schema_version":"1.0","event_id":"sha256:0d33e32d4f1ad4cdec1e687f74560302ebc79e446478414f476bb20bc5c0a659"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SYA4FFT2WRXPLCVZ2DRQDA2QMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning a Prior over Intent via Meta-Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Chelsea Finn, Ellis Ratner, Kelvin Xu, Sergey Levine","submitted_at":"2018-05-31T17:29:25Z","abstract_excerpt":"A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert behavior. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e.g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12573","kind":"arxiv","version":5},"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/1805.12573/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":"2026-07-05T00:11:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y1udu3/PEMQAEViJ2p+lpkn8+jMIPBqb7SnG4G1idFEWh1onFphYJqFBrsTfQjb5Q40FL2G0767hofR0PyzoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:04:12.448376Z"},"content_sha256":"f9d4125fef2380915457ede2ba0f3a12535e8e8a1d589ea520fd72806f3dddd2","schema_version":"1.0","event_id":"sha256:f9d4125fef2380915457ede2ba0f3a12535e8e8a1d589ea520fd72806f3dddd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/bundle.json","state_url":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/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":"2026-08-21T10:04:12Z","links":{"resolver":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG","bundle":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/bundle.json","state":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SYA4FFT2WRXPLCVZ2DRQDA2QMG","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":"8be6d1e522f71ad4ff5110ed097259b885fb8bad16726d3893fd8deaf85178e4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T17:29:25Z","title_canon_sha256":"387c0fc64456f9a8223a00b6533643277731687efed84a6203be132fed7a1d6e"},"schema_version":"1.0","source":{"id":"1805.12573","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12573","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12573v5","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12573","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"pith_short_12","alias_value":"SYA4FFT2WRXP","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"pith_short_16","alias_value":"SYA4FFT2WRXPLCVZ","created_at":"2026-07-05T00:11:46Z"},{"alias_kind":"pith_short_8","alias_value":"SYA4FFT2","created_at":"2026-07-05T00:11:46Z"}],"graph_snapshots":[{"event_id":"sha256:f9d4125fef2380915457ede2ba0f3a12535e8e8a1d589ea520fd72806f3dddd2","target":"graph","created_at":"2026-07-05T00:11:46Z","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/1805.12573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert behavior. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e.g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly dif","authors_text":"Anca Dragan, Chelsea Finn, Ellis Ratner, Kelvin Xu, Sergey Levine","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T17:29:25Z","title":"Learning a Prior over Intent via Meta-Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12573","kind":"arxiv","version":5},"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":"sha256:0d33e32d4f1ad4cdec1e687f74560302ebc79e446478414f476bb20bc5c0a659","target":"record","created_at":"2026-07-05T00:11:46Z","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":"8be6d1e522f71ad4ff5110ed097259b885fb8bad16726d3893fd8deaf85178e4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T17:29:25Z","title_canon_sha256":"387c0fc64456f9a8223a00b6533643277731687efed84a6203be132fed7a1d6e"},"schema_version":"1.0","source":{"id":"1805.12573","kind":"arxiv","version":5}},"canonical_sha256":"9601c2967ab46ef58ab9d0e301835061a8c2136e017df8c07b121f93719ed4b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9601c2967ab46ef58ab9d0e301835061a8c2136e017df8c07b121f93719ed4b9","first_computed_at":"2026-07-05T00:11:46.118790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:46.118790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i3pp+gQJC27AFSsiQeu7i652aX8A+ywgBA4apT9Zu2n5jPiVHeDba+2tScmnmhbNXcZb6GY4BHruPDAsAiP1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:46.119347Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.12573","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d33e32d4f1ad4cdec1e687f74560302ebc79e446478414f476bb20bc5c0a659","sha256:f9d4125fef2380915457ede2ba0f3a12535e8e8a1d589ea520fd72806f3dddd2"],"state_sha256":"e8655bbc500c9e33467611e0d7d74c9225383ce18684fbcb8645d2411fdaf17f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8pswTueIf+sbR4nr9d4qw3R+lgciFGeCSl+m3c48xrwo0FPJP83yBp+ft0TgpMiosDn1SeCODbEU8CCLOCGAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:04:12.453472Z","bundle_sha256":"f30b980ea335593bbcf0dba1af19fde956b3feae17f2e7f1a585c36571cba288"}}