{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3IIHZ4GZWOEVRIP6X3HNUOLNFP","short_pith_number":"pith:3IIHZ4GZ","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"},"canonical_sha256":"da107cf0d9b38958a1febeceda396d2bcb65b90926c5c4efb802d2349092aa26","source":{"kind":"arxiv","id":"2605.12000","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12000","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12000v2","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12000","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"3IIHZ4GZWOEV","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"3IIHZ4GZWOEVRIP6","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"3IIHZ4GZ","created_at":"2026-05-20T00:05:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3IIHZ4GZWOEVRIP6X3HNUOLNFP","target":"record","payload":{"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"},"canonical_sha256":"da107cf0d9b38958a1febeceda396d2bcb65b90926c5c4efb802d2349092aa26","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"},"source_kind":"arxiv","source_id":"2605.12000","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":"2026-05-20T00:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7v0oL4nCpZSOBfesJdzTk16JfHJ9L5+6I0WEhJlR00nBuWXG8z0OKI5RSd34BHMIOGzn2whWb2Pvc14ZCqdXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:10:26.918179Z"},"content_sha256":"99fa1234eeb1b5575bf2462013d5fd81b6bc14a5893cc8652b9a210382a88b7d","schema_version":"1.0","event_id":"sha256:99fa1234eeb1b5575bf2462013d5fd81b6bc14a5893cc8652b9a210382a88b7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3IIHZ4GZWOEVRIP6X3HNUOLNFP","target":"graph","payload":{"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"},"verdict_id":"883292d0-26f6-45c3-ade5-7f2e115f4577"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q7vs+vBKVfO3ApF2H2fbAbzxStG1zWSx51cFSiwsBezORuSJgMlq+UjIDiRktDIuFxd29zJsWs/fEyjMA6N9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:10:26.919139Z"},"content_sha256":"a724c5b4c1393a55c309b76a57a4ed9a630b7f7b10721445c6bf8f93d90da623","schema_version":"1.0","event_id":"sha256:a724c5b4c1393a55c309b76a57a4ed9a630b7f7b10721445c6bf8f93d90da623"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/bundle.json","state_url":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/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":"2026-05-29T21:10:26Z","links":{"resolver":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP","bundle":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/bundle.json","state":"https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3IIHZ4GZWOEVRIP6X3HNUOLNFP","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":"c6b6dd7ef44777e1af2feadaec44b11215e99812b630757889a4f96c9b338b57","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T11:49:08Z","title_canon_sha256":"0c17dc9eafbce2a8a12f8c525fd0b65071b56d6fcc8bffd00211e1ce7ea48fab"},"schema_version":"1.0","source":{"id":"2605.12000","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12000","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12000v2","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12000","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"3IIHZ4GZWOEV","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"3IIHZ4GZWOEVRIP6","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"3IIHZ4GZ","created_at":"2026-05-20T00:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:a724c5b4c1393a55c309b76a57a4ed9a630b7f7b10721445c6bf8f93d90da623","target":"graph","created_at":"2026-05-20T00:05:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MA-BC partitions conflicting expert data and pools the rest to recover Pareto-optimal policies faster than separate learners in multi-objective imitation."}],"snapshot_sha256":"aa6fca9d1b225c6a44f2a7ab877d9b7edf23f5e6a39790128c8929ded3399781"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.12000/integrity.json","findings":[],"snapshot_sha256":"b9d264c700af20b793f1d7bf1693dcbba2479fb34bdfac9841d0021795af17f9","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Claire Vernade, Luca Viano, Volkan Cevher, Ziyad Sheebaelhamd","cross_cats":[],"headline":"MA-BC partitions conflicting expert data and pools the rest to recover Pareto-optimal policies faster than separate learners in multi-objective imitation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T11:49:08Z","title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.12000","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T07:12:17.881078Z","id":"883292d0-26f6-45c3-ade5-7f2e115f4577","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"883292d0-26f6-45c3-ade5-7f2e115f4577"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:99fa1234eeb1b5575bf2462013d5fd81b6bc14a5893cc8652b9a210382a88b7d","target":"record","created_at":"2026-05-20T00:05:47Z","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":"c6b6dd7ef44777e1af2feadaec44b11215e99812b630757889a4f96c9b338b57","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T11:49:08Z","title_canon_sha256":"0c17dc9eafbce2a8a12f8c525fd0b65071b56d6fcc8bffd00211e1ce7ea48fab"},"schema_version":"1.0","source":{"id":"2605.12000","kind":"arxiv","version":2}},"canonical_sha256":"da107cf0d9b38958a1febeceda396d2bcb65b90926c5c4efb802d2349092aa26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da107cf0d9b38958a1febeceda396d2bcb65b90926c5c4efb802d2349092aa26","first_computed_at":"2026-05-20T00:05:47.245557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:47.245557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qWFTRZnQmYPglhesdTt5paO/mRMbeiEiM+qPM0sw3GHV0M6bMsECsYIdnCqEE5Ez8AKYWYdN3W5/0iJc1KZeCg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:47.246178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12000","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99fa1234eeb1b5575bf2462013d5fd81b6bc14a5893cc8652b9a210382a88b7d","sha256:a724c5b4c1393a55c309b76a57a4ed9a630b7f7b10721445c6bf8f93d90da623"],"state_sha256":"61907c7f83c611d0dbd73572bc0c80bbaf9ceb9e101083e34906f675631c681c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"upLcmxJJJGcPxWRDvbYxdl9sMYtad+tqw3Z9x3bQiahdWnRMKYhCmdkDUQkDJPojlnEEAZJP+6mUdInWa9gdCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T21:10:26.923522Z","bundle_sha256":"aef714c0d2e78915aad12f4d6a2d1fe2469a6e76d114531ce0c410e28f709381"}}