{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D5NS2E3GZ2GLLMPKCRALU2EMCS","short_pith_number":"pith:D5NS2E3G","canonical_record":{"source":{"id":"2402.03807","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T08:48:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56e126d6cc8312b5103bec6edcc1608af9a9573cbb8bd7be595e33d33ecec057","abstract_canon_sha256":"e38b8046e513daab0c7e7898f490649fc0bedc11c1db9a7b7477c5e8522a32ba"},"schema_version":"1.0"},"canonical_sha256":"1f5b2d1366ce8cb5b1ea1440ba688c1487e3de34db9c831fcc457b26d15c555d","source":{"kind":"arxiv","id":"2402.03807","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03807","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03807v2","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03807","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"pith_short_12","alias_value":"D5NS2E3GZ2GL","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"pith_short_16","alias_value":"D5NS2E3GZ2GLLMPK","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"pith_short_8","alias_value":"D5NS2E3G","created_at":"2026-07-05T07:47:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D5NS2E3GZ2GLLMPKCRALU2EMCS","target":"record","payload":{"canonical_record":{"source":{"id":"2402.03807","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T08:48:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56e126d6cc8312b5103bec6edcc1608af9a9573cbb8bd7be595e33d33ecec057","abstract_canon_sha256":"e38b8046e513daab0c7e7898f490649fc0bedc11c1db9a7b7477c5e8522a32ba"},"schema_version":"1.0"},"canonical_sha256":"1f5b2d1366ce8cb5b1ea1440ba688c1487e3de34db9c831fcc457b26d15c555d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:28.568427Z","signature_b64":"JPU7KYtduSuZfdn3UMbVnGcsILAGZ+ZIS7vl3Zt/BDgxnb0kCWo9oweiinpBhbAMfD5at7qqD92Y3y1lkH8hAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f5b2d1366ce8cb5b1ea1440ba688c1487e3de34db9c831fcc457b26d15c555d","last_reissued_at":"2026-07-05T07:47:28.567955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:28.567955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.03807","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":"2026-07-05T07:47:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xIMxxzO+DRX6hGx9DQpckFVhIynqkIdsnh7tB4X2DqTKnGR2BlkWq0INIRVOmmTTpnD5bwOe1/FjEYsDlDICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:34:59.256501Z"},"content_sha256":"098797f55ec4794cfa15366b40e3ce14bb33a96b9bed35207b51c2080cb0565e","schema_version":"1.0","event_id":"sha256:098797f55ec4794cfa15366b40e3ce14bb33a96b9bed35207b51c2080cb0565e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D5NS2E3GZ2GLLMPKCRALU2EMCS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiafei Lyu, Le Wan, Runze Liu, Xiaoteng Ma, Xiu Li, Zongqing Lu","submitted_at":"2024-02-06T08:48:01Z","abstract_excerpt":"Offline reinforcement learning (RL) has attracted much attention due to its ability in learning from static offline datasets and eliminating the need of interacting with the environment. Nevertheless, the success of offline RL relies heavily on the offline transitions annotated with reward labels. In practice, we often need to hand-craft the reward function, which is sometimes difficult, labor-intensive, or inefficient. To tackle this challenge, we set our focus on the offline imitation learning (IL) setting, and aim at getting a reward function based on the expert data and unlabeled data. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03807","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/2402.03807/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":"2026-07-05T07:47:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0lmlm/DiJ8L0ch11duQD7uPQR3kpn3LXNmdLcyM7ty28oZQSYe+eOWvjYczDPDNOkg+j9Ib4HsOywvJ7W1XCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:34:59.257087Z"},"content_sha256":"0492e1a7a52e67496b05267d012dc59164dcb01fbd733c695ad1cf93f7c9d445","schema_version":"1.0","event_id":"sha256:0492e1a7a52e67496b05267d012dc59164dcb01fbd733c695ad1cf93f7c9d445"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D5NS2E3GZ2GLLMPKCRALU2EMCS/bundle.json","state_url":"https://pith.science/pith/D5NS2E3GZ2GLLMPKCRALU2EMCS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D5NS2E3GZ2GLLMPKCRALU2EMCS/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":"2026-08-08T05:34:59Z","links":{"resolver":"https://pith.science/pith/D5NS2E3GZ2GLLMPKCRALU2EMCS","bundle":"https://pith.science/pith/D5NS2E3GZ2GLLMPKCRALU2EMCS/bundle.json","state":"https://pith.science/pith/D5NS2E3GZ2GLLMPKCRALU2EMCS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D5NS2E3GZ2GLLMPKCRALU2EMCS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D5NS2E3GZ2GLLMPKCRALU2EMCS","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":"e38b8046e513daab0c7e7898f490649fc0bedc11c1db9a7b7477c5e8522a32ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T08:48:01Z","title_canon_sha256":"56e126d6cc8312b5103bec6edcc1608af9a9573cbb8bd7be595e33d33ecec057"},"schema_version":"1.0","source":{"id":"2402.03807","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03807","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03807v2","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03807","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"pith_short_12","alias_value":"D5NS2E3GZ2GL","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"pith_short_16","alias_value":"D5NS2E3GZ2GLLMPK","created_at":"2026-07-05T07:47:28Z"},{"alias_kind":"pith_short_8","alias_value":"D5NS2E3G","created_at":"2026-07-05T07:47:28Z"}],"graph_snapshots":[{"event_id":"sha256:0492e1a7a52e67496b05267d012dc59164dcb01fbd733c695ad1cf93f7c9d445","target":"graph","created_at":"2026-07-05T07:47:28Z","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/2402.03807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) has attracted much attention due to its ability in learning from static offline datasets and eliminating the need of interacting with the environment. Nevertheless, the success of offline RL relies heavily on the offline transitions annotated with reward labels. In practice, we often need to hand-craft the reward function, which is sometimes difficult, labor-intensive, or inefficient. To tackle this challenge, we set our focus on the offline imitation learning (IL) setting, and aim at getting a reward function based on the expert data and unlabeled data. To ","authors_text":"Jiafei Lyu, Le Wan, Runze Liu, Xiaoteng Ma, Xiu Li, Zongqing Lu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T08:48:01Z","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03807","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":"sha256:098797f55ec4794cfa15366b40e3ce14bb33a96b9bed35207b51c2080cb0565e","target":"record","created_at":"2026-07-05T07:47:28Z","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":"e38b8046e513daab0c7e7898f490649fc0bedc11c1db9a7b7477c5e8522a32ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T08:48:01Z","title_canon_sha256":"56e126d6cc8312b5103bec6edcc1608af9a9573cbb8bd7be595e33d33ecec057"},"schema_version":"1.0","source":{"id":"2402.03807","kind":"arxiv","version":2}},"canonical_sha256":"1f5b2d1366ce8cb5b1ea1440ba688c1487e3de34db9c831fcc457b26d15c555d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f5b2d1366ce8cb5b1ea1440ba688c1487e3de34db9c831fcc457b26d15c555d","first_computed_at":"2026-07-05T07:47:28.567955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:28.567955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JPU7KYtduSuZfdn3UMbVnGcsILAGZ+ZIS7vl3Zt/BDgxnb0kCWo9oweiinpBhbAMfD5at7qqD92Y3y1lkH8hAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:28.568427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03807","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:098797f55ec4794cfa15366b40e3ce14bb33a96b9bed35207b51c2080cb0565e","sha256:0492e1a7a52e67496b05267d012dc59164dcb01fbd733c695ad1cf93f7c9d445"],"state_sha256":"df8a076d9509982154d1535bca6933cc653e5958bfd34957e4c891d6f7716759"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+SwQNv5mYDxN1u+90XbO5Cm6g4XNOn+XjEN/JpfE4uXSSGgsokWw45FTh1prMrGLrm9jiP0fgj+VGU+TrZd1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:34:59.261617Z","bundle_sha256":"5b44123adfe19d4f127a5707e9494f5b35ae6e2001f6e0dfb192c521d79601e1"}}