{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:55Z5NJ3NGHMI2RNMNR3MJSL2ZN","short_pith_number":"pith:55Z5NJ3N","schema_version":"1.0","canonical_sha256":"ef73d6a76d31d88d45ac6c76c4c97acb7d4f389e85287cbf9f0ead5b8967ed66","source":{"kind":"arxiv","id":"2405.17476","version":3},"attestation_state":"computed","paper":{"title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiani Liu, Junshan Zhang, Ju Ren, Sen Lin, Sheng Yue, Xingyuan Hua, Yaoxue Zhang","submitted_at":"2024-05-24T04:56:39Z","abstract_excerpt":"Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy data. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) $\\textit{diverse}$ state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.17476","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T04:56:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c378669f820cb562a176c53ab4622d38bfc71cd950eccecc8a8b81d66347799","abstract_canon_sha256":"3c5f8e7edec09cf66a953b59279ef9c3d6fcea552c63fd8ba4cffb8fdd9ac5dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:05.423276Z","signature_b64":"Nml8qHsMpPk7gM8DfG0lDfUXY0YKJ5Sc0hrLPS0T7qfez8L0BwcB5YvGrxGbgv335nd6/PaTz/6HDlsyE8TyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef73d6a76d31d88d45ac6c76c4c97acb7d4f389e85287cbf9f0ead5b8967ed66","last_reissued_at":"2026-07-05T08:25:05.422741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:05.422741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiani Liu, Junshan Zhang, Ju Ren, Sen Lin, Sheng Yue, Xingyuan Hua, Yaoxue Zhang","submitted_at":"2024-05-24T04:56:39Z","abstract_excerpt":"Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy data. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) $\\textit{diverse}$ state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17476","kind":"arxiv","version":3},"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/2405.17476/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.17476","created_at":"2026-07-05T08:25:05.422812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17476v3","created_at":"2026-07-05T08:25:05.422812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17476","created_at":"2026-07-05T08:25:05.422812+00:00"},{"alias_kind":"pith_short_12","alias_value":"55Z5NJ3NGHMI","created_at":"2026-07-05T08:25:05.422812+00:00"},{"alias_kind":"pith_short_16","alias_value":"55Z5NJ3NGHMI2RNM","created_at":"2026-07-05T08:25:05.422812+00:00"},{"alias_kind":"pith_short_8","alias_value":"55Z5NJ3N","created_at":"2026-07-05T08:25:05.422812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01529","citing_title":"Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01529","citing_title":"Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN","json":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN.json","graph_json":"https://pith.science/api/pith-number/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/graph.json","events_json":"https://pith.science/api/pith-number/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/events.json","paper":"https://pith.science/paper/55Z5NJ3N"},"agent_actions":{"view_html":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN","download_json":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN.json","view_paper":"https://pith.science/paper/55Z5NJ3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17476&json=true","fetch_graph":"https://pith.science/api/pith-number/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/graph.json","fetch_events":"https://pith.science/api/pith-number/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/action/storage_attestation","attest_author":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/action/author_attestation","sign_citation":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/action/citation_signature","submit_replication":"https://pith.science/pith/55Z5NJ3NGHMI2RNMNR3MJSL2ZN/action/replication_record"}},"created_at":"2026-07-05T08:25:05.422812+00:00","updated_at":"2026-07-05T08:25:05.422812+00:00"}