{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3IIHZ4GZWOEVRIP6X3HNUOLNFP","short_pith_number":"pith:3IIHZ4GZ","schema_version":"1.0","canonical_sha256":"da107cf0d9b38958a1febeceda396d2bcb65b90926c5c4efb802d2349092aa26","source":{"kind":"arxiv","id":"2605.12000","version":2},"attestation_state":"computed","paper":{"title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MA-BC partitions conflicting expert data and pools the rest to recover Pareto-optimal policies faster than separate learners in multi-objective imitation.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claire Vernade, Luca Viano, Volkan Cevher, Ziyad Sheebaelhamd","submitted_at":"2026-05-12T11:49:08Z","abstract_excerpt":"This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from multiple Pareto-optimal experts in a Multi-Objective Markov Decision Process (MOMDP). Standard imitation approaches are ill-equipped for this regime, as naively aggregating conflicting expert trajectories can result in dominated policies. To address this, we introduce Multi-Output Augmented Behavioral Cloning (MA-BC), an algorithm that systematically partitions divergent expert data while pooling state-action pairs where no behavior conflict is ob"},"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":"2605.12000","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T11:49:08Z","cross_cats_sorted":[],"title_canon_sha256":"0c17dc9eafbce2a8a12f8c525fd0b65071b56d6fcc8bffd00211e1ce7ea48fab","abstract_canon_sha256":"c6b6dd7ef44777e1af2feadaec44b11215e99812b630757889a4f96c9b338b57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:47.246178Z","signature_b64":"qWFTRZnQmYPglhesdTt5paO/mRMbeiEiM+qPM0sw3GHV0M6bMsECsYIdnCqEE5Ez8AKYWYdN3W5/0iJc1KZeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da107cf0d9b38958a1febeceda396d2bcb65b90926c5c4efb802d2349092aa26","last_reissued_at":"2026-05-20T00:05:47.245557Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:47.245557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MA-BC partitions conflicting expert data and pools the rest to recover Pareto-optimal policies faster than separate learners in multi-objective imitation.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claire Vernade, Luca Viano, Volkan Cevher, Ziyad Sheebaelhamd","submitted_at":"2026-05-12T11:49:08Z","abstract_excerpt":"This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from multiple Pareto-optimal experts in a Multi-Objective Markov Decision Process (MOMDP). Standard imitation approaches are ill-equipped for this regime, as naively aggregating conflicting expert trajectories can result in dominated policies. To address this, we introduce Multi-Output Augmented Behavioral Cloning (MA-BC), an algorithm that systematically partitions divergent expert data while pooling state-action pairs where no behavior conflict is ob"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MA-BC converges to Pareto-optimal policies at a faster statistical rate than any learner that considers each expert dataset independently, and is minimax optimal.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The provided demonstrations come from Pareto-optimal experts in a MOMDP, and that observable conflicts in state-action pairs can be reliably partitioned without additional structure on the transition dynamics or reward functions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MA-BC partitions divergent expert data while pooling non-conflicting pairs in MOMDPs, converging faster to Pareto-optimal policies than independent learners and matching a new minimax lower bound.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MA-BC partitions conflicting expert data and pools the rest to recover Pareto-optimal policies faster than separate learners in multi-objective imitation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"aa6fca9d1b225c6a44f2a7ab877d9b7edf23f5e6a39790128c8929ded3399781"},"source":{"id":"2605.12000","kind":"arxiv","version":2},"verdict":{"id":"883292d0-26f6-45c3-ade5-7f2e115f4577","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T07:12:17.881078Z","strongest_claim":"MA-BC converges to Pareto-optimal policies at a faster statistical rate than any learner that considers each expert dataset independently, and is minimax optimal.","one_line_summary":"MA-BC partitions divergent expert data while pooling non-conflicting pairs in MOMDPs, converging faster to Pareto-optimal policies than independent learners and matching a new minimax lower bound.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The provided demonstrations come from Pareto-optimal experts in a MOMDP, and that observable conflicts in state-action pairs can be reliably partitioned without additional structure on the transition dynamics or reward functions.","pith_extraction_headline":"MA-BC partitions conflicting expert data and pools the rest to recover Pareto-optimal policies faster than separate learners in multi-objective imitation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.12000/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T11:34:32.698951Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T09:01:16.975212Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T07:59:15.381795Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b9d264c700af20b793f1d7bf1693dcbba2479fb34bdfac9841d0021795af17f9"},"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":"2605.12000","created_at":"2026-05-20T00:05:47.245649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12000v2","created_at":"2026-05-20T00:05:47.245649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12000","created_at":"2026-05-20T00:05:47.245649+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IIHZ4GZWOEV","created_at":"2026-05-20T00:05:47.245649+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IIHZ4GZWOEVRIP6","created_at":"2026-05-20T00:05:47.245649+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IIHZ4GZ","created_at":"2026-05-20T00:05:47.245649+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/3IIHZ4GZWOEVRIP6X3HNUOLNFP","json":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP.json","graph_json":"https://pith.science/api/pith-number/3IIHZ4GZWOEVRIP6X3HNUOLNFP/graph.json","events_json":"https://pith.science/api/pith-number/3IIHZ4GZWOEVRIP6X3HNUOLNFP/events.json","paper":"https://pith.science/paper/3IIHZ4GZ"},"agent_actions":{"view_html":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP","download_json":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP.json","view_paper":"https://pith.science/paper/3IIHZ4GZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12000&json=true","fetch_graph":"https://pith.science/api/pith-number/3IIHZ4GZWOEVRIP6X3HNUOLNFP/graph.json","fetch_events":"https://pith.science/api/pith-number/3IIHZ4GZWOEVRIP6X3HNUOLNFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/action/storage_attestation","attest_author":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/action/author_attestation","sign_citation":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/action/citation_signature","submit_replication":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/action/replication_record"}},"created_at":"2026-05-20T00:05:47.245649+00:00","updated_at":"2026-05-20T00:05:47.245649+00:00"}