{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:66VL7ULNW4PESHMNJUAYUHPBGJ","short_pith_number":"pith:66VL7ULN","canonical_record":{"source":{"id":"2310.08823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T02:38:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfe9cb71f65bb7cb8abd2c184585f3a4593e5707a90238f37ea558368184d43a","abstract_canon_sha256":"32ec8b9f0d5d99e887595afeecbb74ca17dce7c6aa0b8fd13e69b52f9cb7e06c"},"schema_version":"1.0"},"canonical_sha256":"f7aabfd16db71e491d8d4d018a1de1327e984591202931bd71615a33727aa30d","source":{"kind":"arxiv","id":"2310.08823","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08823","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08823v1","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08823","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"66VL7ULNW4PE","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"66VL7ULNW4PESHMN","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"66VL7ULN","created_at":"2026-07-05T07:00:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:66VL7ULNW4PESHMNJUAYUHPBGJ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.08823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T02:38:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfe9cb71f65bb7cb8abd2c184585f3a4593e5707a90238f37ea558368184d43a","abstract_canon_sha256":"32ec8b9f0d5d99e887595afeecbb74ca17dce7c6aa0b8fd13e69b52f9cb7e06c"},"schema_version":"1.0"},"canonical_sha256":"f7aabfd16db71e491d8d4d018a1de1327e984591202931bd71615a33727aa30d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:35.405823Z","signature_b64":"fLRYdi71/oAU9Y66mhwmCR5wfB6ZhNdWUOKQdYsI579ezGT3cYwzgjVwrCdPotqESUUBS/amwcVTdgxM4SQWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7aabfd16db71e491d8d4d018a1de1327e984591202931bd71615a33727aa30d","last_reissued_at":"2026-07-05T07:00:35.405355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:35.405355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.08823","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":"2026-07-05T07:00:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ui6d2u3SMrz83JFUwFrwvex4+z0vqWsjh0tXqE7kcTbxYjyWeSIj6p6lkij6bCXEQ/yc0MUH7a4dG/G9gBoRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:50:09.427991Z"},"content_sha256":"8c4b27d7ef408c5863c7aa5030a1c86c7ac5d72b784ffee867f23d0c3404ed2e","schema_version":"1.0","event_id":"sha256:8c4b27d7ef408c5863c7aa5030a1c86c7ac5d72b784ffee867f23d0c3404ed2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:66VL7ULNW4PESHMNJUAYUHPBGJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jie Liu, Lu Li, Ruobing Chen, Yu Liu, Yuxin Pan, Zhiheng Li, Zilin Wang","submitted_at":"2023-10-13T02:38:35Z","abstract_excerpt":"Inverse reinforcement learning (IRL) aims to explicitly infer an underlying reward function based on collected expert demonstrations. Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on learning a better-than-demonstrator policy using a reward function derived from sub-optimal demonstrations. However, existing IRL algorithms primarily tackle the challenge of trajectory ranking ambiguity when learning the reward function. They overlook the crucial role of considering the degree of difference between trajectories in terms of their returns, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08823","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/2310.08823/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":"2026-07-05T07:00:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yO3iP0nt17u5i0mYj0WsD8M1Fi01s4hs1ANUBG3XAYAZTr+uJ0rttggZTT28HjY4PTInc7jxh51zKjT50ackBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:50:09.428525Z"},"content_sha256":"6573a72ecdc4a2aa35516e1b0386416841464edbe19a47668c7396d4fdb38a0a","schema_version":"1.0","event_id":"sha256:6573a72ecdc4a2aa35516e1b0386416841464edbe19a47668c7396d4fdb38a0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/66VL7ULNW4PESHMNJUAYUHPBGJ/bundle.json","state_url":"https://pith.science/pith/66VL7ULNW4PESHMNJUAYUHPBGJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/66VL7ULNW4PESHMNJUAYUHPBGJ/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":"2026-08-23T09:50:09Z","links":{"resolver":"https://pith.science/pith/66VL7ULNW4PESHMNJUAYUHPBGJ","bundle":"https://pith.science/pith/66VL7ULNW4PESHMNJUAYUHPBGJ/bundle.json","state":"https://pith.science/pith/66VL7ULNW4PESHMNJUAYUHPBGJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/66VL7ULNW4PESHMNJUAYUHPBGJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:66VL7ULNW4PESHMNJUAYUHPBGJ","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":"32ec8b9f0d5d99e887595afeecbb74ca17dce7c6aa0b8fd13e69b52f9cb7e06c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T02:38:35Z","title_canon_sha256":"cfe9cb71f65bb7cb8abd2c184585f3a4593e5707a90238f37ea558368184d43a"},"schema_version":"1.0","source":{"id":"2310.08823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08823","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08823v1","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08823","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"66VL7ULNW4PE","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"66VL7ULNW4PESHMN","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"66VL7ULN","created_at":"2026-07-05T07:00:35Z"}],"graph_snapshots":[{"event_id":"sha256:6573a72ecdc4a2aa35516e1b0386416841464edbe19a47668c7396d4fdb38a0a","target":"graph","created_at":"2026-07-05T07:00:35Z","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/2310.08823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse reinforcement learning (IRL) aims to explicitly infer an underlying reward function based on collected expert demonstrations. Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on learning a better-than-demonstrator policy using a reward function derived from sub-optimal demonstrations. However, existing IRL algorithms primarily tackle the challenge of trajectory ranking ambiguity when learning the reward function. They overlook the crucial role of considering the degree of difference between trajectories in terms of their returns, wh","authors_text":"Jie Liu, Lu Li, Ruobing Chen, Yu Liu, Yuxin Pan, Zhiheng Li, Zilin Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T02:38:35Z","title":"Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08823","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":"sha256:8c4b27d7ef408c5863c7aa5030a1c86c7ac5d72b784ffee867f23d0c3404ed2e","target":"record","created_at":"2026-07-05T07:00:35Z","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":"32ec8b9f0d5d99e887595afeecbb74ca17dce7c6aa0b8fd13e69b52f9cb7e06c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T02:38:35Z","title_canon_sha256":"cfe9cb71f65bb7cb8abd2c184585f3a4593e5707a90238f37ea558368184d43a"},"schema_version":"1.0","source":{"id":"2310.08823","kind":"arxiv","version":1}},"canonical_sha256":"f7aabfd16db71e491d8d4d018a1de1327e984591202931bd71615a33727aa30d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7aabfd16db71e491d8d4d018a1de1327e984591202931bd71615a33727aa30d","first_computed_at":"2026-07-05T07:00:35.405355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:35.405355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fLRYdi71/oAU9Y66mhwmCR5wfB6ZhNdWUOKQdYsI579ezGT3cYwzgjVwrCdPotqESUUBS/amwcVTdgxM4SQWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:35.405823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c4b27d7ef408c5863c7aa5030a1c86c7ac5d72b784ffee867f23d0c3404ed2e","sha256:6573a72ecdc4a2aa35516e1b0386416841464edbe19a47668c7396d4fdb38a0a"],"state_sha256":"3a13241ed735d1c3c7f89ca132c37cdb259a484ea3013f420e802faeaf8979f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngrmQ9FJn8NItHYaB3hs1zZ9PyTokJ033SUK0oqnPQ4CDovJmYaUcumSchv/Szmh4MeIExCz3b/UnDtW3x6FBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T09:50:09.432836Z","bundle_sha256":"af649f806a5a5fd6eb0cafcf91eecfefed519052a5b49491ea98fad86b5e0dd2"}}