{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P47XIDY3BZICCR7PKHRZUHAPA3","short_pith_number":"pith:P47XIDY3","schema_version":"1.0","canonical_sha256":"7f3f740f1b0e502147ef51e39a1c0f06f159d14ee6a805809c00ae7548655c84","source":{"kind":"arxiv","id":"2301.11734","version":2},"attestation_state":"computed","paper":{"title":"Improving Behavioural Cloning with Positive Unlabeled Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"David Cordova Bulens, Felix Widmaier, Francisco Roldan Sanchez, Kevin McGuinness, Nico G\\\"urtler, Noel E. O'Connor, Qiang Wang, Robert McCarthy, Stephen J. Redmond","submitted_at":"2023-01-27T14:17:45Z","abstract_excerpt":"Learning control policies offline from pre-recorded datasets is a promising avenue for solving challenging real-world problems. However, available datasets are typically of mixed quality, with a limited number of the trajectories that we would consider as positive examples; i.e., high-quality demonstrations. Therefore, we propose a novel iterative learning algorithm for identifying expert trajectories in unlabeled mixed-quality robotics datasets given a minimal set of positive examples, surpassing existing algorithms in terms of accuracy. We show that applying behavioral cloning to the resulti"},"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":"2301.11734","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T14:17:45Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"48c309a8dadc63e943b81fd4f81c1dc1921d531e018d860923837f6ab6d9fcdc","abstract_canon_sha256":"d6baf4df95c1ceb4afc351c721391609c603dc8936ee0f12ea54e89a6f46f58f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:45.474401Z","signature_b64":"udBV1WZsLs3VtWsF+WI03UgEbr8DIT90MCSgez0Ek/n1kXb1wcMfpllspGIyNKVBZfC7tZeKD+Vs9qDP68SiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f3f740f1b0e502147ef51e39a1c0f06f159d14ee6a805809c00ae7548655c84","last_reissued_at":"2026-07-05T06:52:45.473861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:45.473861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Behavioural Cloning with Positive Unlabeled Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"David Cordova Bulens, Felix Widmaier, Francisco Roldan Sanchez, Kevin McGuinness, Nico G\\\"urtler, Noel E. O'Connor, Qiang Wang, Robert McCarthy, Stephen J. Redmond","submitted_at":"2023-01-27T14:17:45Z","abstract_excerpt":"Learning control policies offline from pre-recorded datasets is a promising avenue for solving challenging real-world problems. However, available datasets are typically of mixed quality, with a limited number of the trajectories that we would consider as positive examples; i.e., high-quality demonstrations. Therefore, we propose a novel iterative learning algorithm for identifying expert trajectories in unlabeled mixed-quality robotics datasets given a minimal set of positive examples, surpassing existing algorithms in terms of accuracy. We show that applying behavioral cloning to the resulti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11734","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/2301.11734/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":"2301.11734","created_at":"2026-07-05T06:52:45.473924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11734v2","created_at":"2026-07-05T06:52:45.473924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11734","created_at":"2026-07-05T06:52:45.473924+00:00"},{"alias_kind":"pith_short_12","alias_value":"P47XIDY3BZIC","created_at":"2026-07-05T06:52:45.473924+00:00"},{"alias_kind":"pith_short_16","alias_value":"P47XIDY3BZICCR7P","created_at":"2026-07-05T06:52:45.473924+00:00"},{"alias_kind":"pith_short_8","alias_value":"P47XIDY3","created_at":"2026-07-05T06:52:45.473924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05429","citing_title":"Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3","json":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3.json","graph_json":"https://pith.science/api/pith-number/P47XIDY3BZICCR7PKHRZUHAPA3/graph.json","events_json":"https://pith.science/api/pith-number/P47XIDY3BZICCR7PKHRZUHAPA3/events.json","paper":"https://pith.science/paper/P47XIDY3"},"agent_actions":{"view_html":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3","download_json":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3.json","view_paper":"https://pith.science/paper/P47XIDY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11734&json=true","fetch_graph":"https://pith.science/api/pith-number/P47XIDY3BZICCR7PKHRZUHAPA3/graph.json","fetch_events":"https://pith.science/api/pith-number/P47XIDY3BZICCR7PKHRZUHAPA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3/action/storage_attestation","attest_author":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3/action/author_attestation","sign_citation":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3/action/citation_signature","submit_replication":"https://pith.science/pith/P47XIDY3BZICCR7PKHRZUHAPA3/action/replication_record"}},"created_at":"2026-07-05T06:52:45.473924+00:00","updated_at":"2026-07-05T06:52:45.473924+00:00"}