{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7XTURZHJ5G54K73722VV5H3WPD","short_pith_number":"pith:7XTURZHJ","canonical_record":{"source":{"id":"2310.12055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T15:42:53Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"9378f7180f3700ece86c7d7bb74efb7d33d5ce771a52fcbfe02db00ef191721a","abstract_canon_sha256":"bef7dd7ab8229964dfbea0c2ba991dd113dceebd243cdef2c490efe435e7353b"},"schema_version":"1.0"},"canonical_sha256":"fde748e4e9e9bbc57f7fd6ab5e9f7678d7a58c4277d944c4c0acf00e35083b66","source":{"kind":"arxiv","id":"2310.12055","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12055","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12055v1","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12055","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"7XTURZHJ5G54","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"7XTURZHJ5G54K737","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"7XTURZHJ","created_at":"2026-07-05T07:02:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7XTURZHJ5G54K73722VV5H3WPD","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T15:42:53Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"9378f7180f3700ece86c7d7bb74efb7d33d5ce771a52fcbfe02db00ef191721a","abstract_canon_sha256":"bef7dd7ab8229964dfbea0c2ba991dd113dceebd243cdef2c490efe435e7353b"},"schema_version":"1.0"},"canonical_sha256":"fde748e4e9e9bbc57f7fd6ab5e9f7678d7a58c4277d944c4c0acf00e35083b66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:15.741789Z","signature_b64":"0yyIoPRPgfwTFzzwFTtPjYHP4+m0FsLDsgCVRgprHI3u5RYYJWHu+PiKx9NIF5nHOm5YKw4T/0Hhl2i5IUAqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fde748e4e9e9bbc57f7fd6ab5e9f7678d7a58c4277d944c4c0acf00e35083b66","last_reissued_at":"2026-07-05T07:02:15.741289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:15.741289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12055","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":"2026-07-05T07:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXwvfXqOda0Y4Y8L+MBPMu4CUtVyec/xz5kHpkRWmlkwYuO6o1UUx6Y9Yn5w7IR/+9Ndq/NytLysQ6//SFw+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:15:04.036206Z"},"content_sha256":"b9a92f9e2e6fd047279c31ee57e57067b266bf99e6347a9cb22f94390b124969","schema_version":"1.0","event_id":"sha256:b9a92f9e2e6fd047279c31ee57e57067b266bf99e6347a9cb22f94390b124969"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7XTURZHJ5G54K73722VV5H3WPD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Reward Ambiguity Through Optimal Transport Theory in Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Ali Baheri","submitted_at":"2023-10-18T15:42:53Z","abstract_excerpt":"In inverse reinforcement learning (IRL), the central objective is to infer underlying reward functions from observed expert behaviors in a way that not only explains the given data but also generalizes to unseen scenarios. This ensures robustness against reward ambiguity where multiple reward functions can equally explain the same expert behaviors. While significant efforts have been made in addressing this issue, current methods often face challenges with high-dimensional problems and lack a geometric foundation. This paper harnesses the optimal transport (OT) theory to provide a fresh perspe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12055","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/2310.12055/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":"2026-07-05T07:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVFwUPCuKCURfORkY0iDuOpAMAlKqRYeRqf8lzEUWO7S69YbEp4ah7in4nD2MUOQwndnkjNgw0TsiUKW03LkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:15:04.036813Z"},"content_sha256":"146e1ca7679e892ce5598b6ac998a7298e2c638590e992ff3db1244b26ecb4d2","schema_version":"1.0","event_id":"sha256:146e1ca7679e892ce5598b6ac998a7298e2c638590e992ff3db1244b26ecb4d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XTURZHJ5G54K73722VV5H3WPD/bundle.json","state_url":"https://pith.science/pith/7XTURZHJ5G54K73722VV5H3WPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XTURZHJ5G54K73722VV5H3WPD/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":"2026-08-09T04:15:04Z","links":{"resolver":"https://pith.science/pith/7XTURZHJ5G54K73722VV5H3WPD","bundle":"https://pith.science/pith/7XTURZHJ5G54K73722VV5H3WPD/bundle.json","state":"https://pith.science/pith/7XTURZHJ5G54K73722VV5H3WPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XTURZHJ5G54K73722VV5H3WPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7XTURZHJ5G54K73722VV5H3WPD","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":"bef7dd7ab8229964dfbea0c2ba991dd113dceebd243cdef2c490efe435e7353b","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T15:42:53Z","title_canon_sha256":"9378f7180f3700ece86c7d7bb74efb7d33d5ce771a52fcbfe02db00ef191721a"},"schema_version":"1.0","source":{"id":"2310.12055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12055","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12055v1","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12055","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"7XTURZHJ5G54","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"7XTURZHJ5G54K737","created_at":"2026-07-05T07:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"7XTURZHJ","created_at":"2026-07-05T07:02:15Z"}],"graph_snapshots":[{"event_id":"sha256:146e1ca7679e892ce5598b6ac998a7298e2c638590e992ff3db1244b26ecb4d2","target":"graph","created_at":"2026-07-05T07:02:15Z","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/2310.12055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In inverse reinforcement learning (IRL), the central objective is to infer underlying reward functions from observed expert behaviors in a way that not only explains the given data but also generalizes to unseen scenarios. This ensures robustness against reward ambiguity where multiple reward functions can equally explain the same expert behaviors. While significant efforts have been made in addressing this issue, current methods often face challenges with high-dimensional problems and lack a geometric foundation. This paper harnesses the optimal transport (OT) theory to provide a fresh perspe","authors_text":"Ali Baheri","cross_cats":["cs.SY","eess.SY","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T15:42:53Z","title":"Understanding Reward Ambiguity Through Optimal Transport Theory in Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12055","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:b9a92f9e2e6fd047279c31ee57e57067b266bf99e6347a9cb22f94390b124969","target":"record","created_at":"2026-07-05T07:02:15Z","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":"bef7dd7ab8229964dfbea0c2ba991dd113dceebd243cdef2c490efe435e7353b","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T15:42:53Z","title_canon_sha256":"9378f7180f3700ece86c7d7bb74efb7d33d5ce771a52fcbfe02db00ef191721a"},"schema_version":"1.0","source":{"id":"2310.12055","kind":"arxiv","version":1}},"canonical_sha256":"fde748e4e9e9bbc57f7fd6ab5e9f7678d7a58c4277d944c4c0acf00e35083b66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fde748e4e9e9bbc57f7fd6ab5e9f7678d7a58c4277d944c4c0acf00e35083b66","first_computed_at":"2026-07-05T07:02:15.741289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:15.741289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0yyIoPRPgfwTFzzwFTtPjYHP4+m0FsLDsgCVRgprHI3u5RYYJWHu+PiKx9NIF5nHOm5YKw4T/0Hhl2i5IUAqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:15.741789Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9a92f9e2e6fd047279c31ee57e57067b266bf99e6347a9cb22f94390b124969","sha256:146e1ca7679e892ce5598b6ac998a7298e2c638590e992ff3db1244b26ecb4d2"],"state_sha256":"f025d1d4a7c82c4ebb6b5f9edc764b61b5857adf649e8e6aae4191bfd4b53ca1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uFsPaVPVgHAqSP5vWFiQTepzLYCtSTWJCNsdcAYJboXqsNy/GhMQ2REcjSTvd4YeJoTkNplZeIvYcP5u8FDSBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:15:04.040341Z","bundle_sha256":"877a3a84439e7eaf9ecc695aafdb02f1f8a30860f10be6ba8e77f37fa818d0df"}}