{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LHPWRCANXLUWK4GALKRNYLADG6","short_pith_number":"pith:LHPWRCAN","canonical_record":{"source":{"id":"2303.16194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T17:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"efe98e04fc89a7c23110d3e6bc60311c941abfd6c9bfd41c3f44086d0ef29709","abstract_canon_sha256":"8847353a0af4c108a78c3cb25a3890ff3cb32bc32783e2849ba98ec05480c60a"},"schema_version":"1.0"},"canonical_sha256":"59df68880dbae96570c05aa2dc2c0337b0e67f8e7b17dc7712fe3d4d36a51752","source":{"kind":"arxiv","id":"2303.16194","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16194","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16194v1","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16194","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"pith_short_12","alias_value":"LHPWRCANXLUW","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"pith_short_16","alias_value":"LHPWRCANXLUWK4GA","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"pith_short_8","alias_value":"LHPWRCAN","created_at":"2026-07-05T05:55:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LHPWRCANXLUWK4GALKRNYLADG6","target":"record","payload":{"canonical_record":{"source":{"id":"2303.16194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T17:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"efe98e04fc89a7c23110d3e6bc60311c941abfd6c9bfd41c3f44086d0ef29709","abstract_canon_sha256":"8847353a0af4c108a78c3cb25a3890ff3cb32bc32783e2849ba98ec05480c60a"},"schema_version":"1.0"},"canonical_sha256":"59df68880dbae96570c05aa2dc2c0337b0e67f8e7b17dc7712fe3d4d36a51752","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:32.971353Z","signature_b64":"+blthsSOhr1P8XSZ2+ewApuuljGfrjUUmHwKZbhSVtcBC0aavRG/OpUiNaM2RrBXli/pxJFYyKyckS4EEQFRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59df68880dbae96570c05aa2dc2c0337b0e67f8e7b17dc7712fe3d4d36a51752","last_reissued_at":"2026-07-05T05:55:32.970911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:32.970911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.16194","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":"2026-07-05T05:55:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LwdZWbT6ELBcGVW2U5LyE6FmIpCMoCuObk+J/mmuIh9KAKcDmQI7fGsuCy+9cUW9msa5zq/tHuWF3GaRbi1/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:35:38.643612Z"},"content_sha256":"b43bb6a8f412e764be2dba28a4e702041da13d23263e5d8939d85ed137efb6f1","schema_version":"1.0","event_id":"sha256:b43bb6a8f412e764be2dba28a4e702041da13d23263e5d8939d85ed137efb6f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LHPWRCANXLUWK4GALKRNYLADG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BC-IRL: Learning Generalizable Reward Functions from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Andrew Szot, Dhruv Batra, Franziska Meier, Zsolt Kira","submitted_at":"2023-03-28T17:57:20Z","abstract_excerpt":"How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy objective, learn rewards that overfit to the demonstrations. Such rewards struggle to provide meaningful rewards for states not covered by the demonstrations, a major detriment when using the reward to learn policies in new situations. We introduce BC-IRL a new inverse reinforcement learning method that learns reward functions that generalize better when compared to maximum-entropy IRL approaches. In contrast to the MaxE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16194","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/2303.16194/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":"2026-07-05T05:55:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IhFhr11Dh/4mTjjZ9HywuqHCMv9jugls6t8TJG8bTnNvCCLuzRKQ5ZoHB9+5Bvu/WGdlKA1+ANZqXr4TbnrmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:35:38.644136Z"},"content_sha256":"0fd0d45a42054d3f041c94eb7cbd3a287562765a6f9161e22c6206b127f243ed","schema_version":"1.0","event_id":"sha256:0fd0d45a42054d3f041c94eb7cbd3a287562765a6f9161e22c6206b127f243ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHPWRCANXLUWK4GALKRNYLADG6/bundle.json","state_url":"https://pith.science/pith/LHPWRCANXLUWK4GALKRNYLADG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHPWRCANXLUWK4GALKRNYLADG6/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":"2026-08-20T01:35:38Z","links":{"resolver":"https://pith.science/pith/LHPWRCANXLUWK4GALKRNYLADG6","bundle":"https://pith.science/pith/LHPWRCANXLUWK4GALKRNYLADG6/bundle.json","state":"https://pith.science/pith/LHPWRCANXLUWK4GALKRNYLADG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHPWRCANXLUWK4GALKRNYLADG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LHPWRCANXLUWK4GALKRNYLADG6","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":"8847353a0af4c108a78c3cb25a3890ff3cb32bc32783e2849ba98ec05480c60a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T17:57:20Z","title_canon_sha256":"efe98e04fc89a7c23110d3e6bc60311c941abfd6c9bfd41c3f44086d0ef29709"},"schema_version":"1.0","source":{"id":"2303.16194","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16194","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16194v1","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16194","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"pith_short_12","alias_value":"LHPWRCANXLUW","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"pith_short_16","alias_value":"LHPWRCANXLUWK4GA","created_at":"2026-07-05T05:55:32Z"},{"alias_kind":"pith_short_8","alias_value":"LHPWRCAN","created_at":"2026-07-05T05:55:32Z"}],"graph_snapshots":[{"event_id":"sha256:0fd0d45a42054d3f041c94eb7cbd3a287562765a6f9161e22c6206b127f243ed","target":"graph","created_at":"2026-07-05T05:55:32Z","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/2303.16194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy objective, learn rewards that overfit to the demonstrations. Such rewards struggle to provide meaningful rewards for states not covered by the demonstrations, a major detriment when using the reward to learn policies in new situations. We introduce BC-IRL a new inverse reinforcement learning method that learns reward functions that generalize better when compared to maximum-entropy IRL approaches. In contrast to the MaxE","authors_text":"Amy Zhang, Andrew Szot, Dhruv Batra, Franziska Meier, Zsolt Kira","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T17:57:20Z","title":"BC-IRL: Learning Generalizable Reward Functions from Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16194","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:b43bb6a8f412e764be2dba28a4e702041da13d23263e5d8939d85ed137efb6f1","target":"record","created_at":"2026-07-05T05:55:32Z","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":"8847353a0af4c108a78c3cb25a3890ff3cb32bc32783e2849ba98ec05480c60a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T17:57:20Z","title_canon_sha256":"efe98e04fc89a7c23110d3e6bc60311c941abfd6c9bfd41c3f44086d0ef29709"},"schema_version":"1.0","source":{"id":"2303.16194","kind":"arxiv","version":1}},"canonical_sha256":"59df68880dbae96570c05aa2dc2c0337b0e67f8e7b17dc7712fe3d4d36a51752","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59df68880dbae96570c05aa2dc2c0337b0e67f8e7b17dc7712fe3d4d36a51752","first_computed_at":"2026-07-05T05:55:32.970911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:55:32.970911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+blthsSOhr1P8XSZ2+ewApuuljGfrjUUmHwKZbhSVtcBC0aavRG/OpUiNaM2RrBXli/pxJFYyKyckS4EEQFRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:55:32.971353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.16194","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b43bb6a8f412e764be2dba28a4e702041da13d23263e5d8939d85ed137efb6f1","sha256:0fd0d45a42054d3f041c94eb7cbd3a287562765a6f9161e22c6206b127f243ed"],"state_sha256":"80f7936baaf970d3c449455dc9d24191650a73886c53d5b99e910f0f190d0ae2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duDDEhjcaXepCBk84IIdWUjna2V8f5a8Wo3u2L4LqHQIOV7MreEixu9STmS7d3KG00+/4aXi4djqRIL7RTkKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:35:38.649952Z","bundle_sha256":"a5eae09c1b03e97ba88e70d00a576f80f5794f7fd63486f3d3a4368abb62f1e3"}}