{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WMB3SA4SBJVLWGD7T5WU5PIE6X","short_pith_number":"pith:WMB3SA4S","schema_version":"1.0","canonical_sha256":"b303b903920a6abb187f9f6d4ebd04f5cc62081bbde1d4765f5da0e7a31271f6","source":{"kind":"arxiv","id":"2504.18160","version":1},"attestation_state":"computed","paper":{"title":"Offline Learning of Controllable Diverse Behaviors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ludovic Denoyer, Mathieu Petitbois, R\\'emy Portelas, Sylvain Lamprier","submitted_at":"2025-04-25T08:16:56Z","abstract_excerpt":"Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks. While IL has gained prominence due to its effectiveness and efficiency, traditional methods often focus on datasets collected from experts to produce a single efficient policy. Recently, extensions have been proposed to handle datasets of diverse behaviors by mainly focusing on learning transition-level diverse policies or on performing entropy maximization at the trajectory level. While these methods may lead to diverse behaviors, they may not be sufficient to reproduce the actual diversity of demonstration"},"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":"2504.18160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T08:16:56Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"dda7e6b9f3d35391b828110ef1a1b78ca31ab5d6b304f960926d9219ba251165","abstract_canon_sha256":"fdbe2506b3b400385ff5f1e45dafebd69b8669dfd3f656ba07c8352542f63ba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:02.981905Z","signature_b64":"XotVXNiFFvikeVUkbjC5JtJQCFVKHnc/4aZmdh+5SeXRaaHj3ORXVA9k8yjs3bE13yy3PX5wSgvFa6SMtnfjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b303b903920a6abb187f9f6d4ebd04f5cc62081bbde1d4765f5da0e7a31271f6","last_reissued_at":"2026-07-05T10:54:02.981439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:02.981439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Learning of Controllable Diverse Behaviors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ludovic Denoyer, Mathieu Petitbois, R\\'emy Portelas, Sylvain Lamprier","submitted_at":"2025-04-25T08:16:56Z","abstract_excerpt":"Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks. While IL has gained prominence due to its effectiveness and efficiency, traditional methods often focus on datasets collected from experts to produce a single efficient policy. Recently, extensions have been proposed to handle datasets of diverse behaviors by mainly focusing on learning transition-level diverse policies or on performing entropy maximization at the trajectory level. While these methods may lead to diverse behaviors, they may not be sufficient to reproduce the actual diversity of demonstration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18160","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/2504.18160/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":"2504.18160","created_at":"2026-07-05T10:54:02.981493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18160v1","created_at":"2026-07-05T10:54:02.981493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18160","created_at":"2026-07-05T10:54:02.981493+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMB3SA4SBJVL","created_at":"2026-07-05T10:54:02.981493+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMB3SA4SBJVLWGD7","created_at":"2026-07-05T10:54:02.981493+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMB3SA4S","created_at":"2026-07-05T10:54:02.981493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X","json":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X.json","graph_json":"https://pith.science/api/pith-number/WMB3SA4SBJVLWGD7T5WU5PIE6X/graph.json","events_json":"https://pith.science/api/pith-number/WMB3SA4SBJVLWGD7T5WU5PIE6X/events.json","paper":"https://pith.science/paper/WMB3SA4S"},"agent_actions":{"view_html":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X","download_json":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X.json","view_paper":"https://pith.science/paper/WMB3SA4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18160&json=true","fetch_graph":"https://pith.science/api/pith-number/WMB3SA4SBJVLWGD7T5WU5PIE6X/graph.json","fetch_events":"https://pith.science/api/pith-number/WMB3SA4SBJVLWGD7T5WU5PIE6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X/action/storage_attestation","attest_author":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X/action/author_attestation","sign_citation":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X/action/citation_signature","submit_replication":"https://pith.science/pith/WMB3SA4SBJVLWGD7T5WU5PIE6X/action/replication_record"}},"created_at":"2026-07-05T10:54:02.981493+00:00","updated_at":"2026-07-05T10:54:02.981493+00:00"}