{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5MK3DEVQMN47Z6BK5IGJULANEI","short_pith_number":"pith:5MK3DEVQ","canonical_record":{"source":{"id":"2601.22823","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T10:49:22Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"444b53ca82e817acb064e970e5b223c5b15d970633e4bd2e6298973d23c7aac4","abstract_canon_sha256":"bcf3177d0a6779640d152acfaa0c2cad84d4ad17889f3d9da4595214b53b2fa8"},"schema_version":"1.0"},"canonical_sha256":"eb15b192b06379fcf82aea0c9a2c0d222de62dafc643971872da51f4d2de8fdf","source":{"kind":"arxiv","id":"2601.22823","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22823","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22823v2","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22823","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"5MK3DEVQMN47","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"5MK3DEVQMN47Z6BK","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"5MK3DEVQ","created_at":"2026-06-30T01:17:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5MK3DEVQMN47Z6BK5IGJULANEI","target":"record","payload":{"canonical_record":{"source":{"id":"2601.22823","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T10:49:22Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"444b53ca82e817acb064e970e5b223c5b15d970633e4bd2e6298973d23c7aac4","abstract_canon_sha256":"bcf3177d0a6779640d152acfaa0c2cad84d4ad17889f3d9da4595214b53b2fa8"},"schema_version":"1.0"},"canonical_sha256":"eb15b192b06379fcf82aea0c9a2c0d222de62dafc643971872da51f4d2de8fdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:33.300694Z","signature_b64":"UkVj9K9z7aUXITpDo08TzDxYWt32HpY9KePUaV1dM2cSc9YGiuTraq0PUcAvgXoVx6w5ucWD87+aH6fizWL+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb15b192b06379fcf82aea0c9a2c0d222de62dafc643971872da51f4d2de8fdf","last_reissued_at":"2026-06-30T01:17:33.299875Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:33.299875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.22823","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":"2026-06-30T01:17:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GBkCMDm2MNjGXkRvgmZcOrPU+OQX+dXJ6TV5Z4HvV/EJJcpNyiR74eu/D2E+rtB0wSHRbMsfLZfFxDd96z8OAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:15:33.440050Z"},"content_sha256":"095021bce9c6cf32f07e3f237ceaf87208db878c438f77dd606f46dc9ef8c9ec","schema_version":"1.0","event_id":"sha256:095021bce9c6cf32f07e3f237ceaf87208db878c438f77dd606f46dc9ef8c9ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5MK3DEVQMN47Z6BK5IGJULANEI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Mathieu Petitbois, R\\'emy Portelas, Sylvain Lamprier","submitted_at":"2026-01-30T10:49:22Z","abstract_excerpt":"We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to distribution shift and inherent conflicts between style and reward. Existing methods, despite introducing numerous definitions of style, often fail to reconcile these objectives effectively. To address these challenges, we propose a unified definition of behavior style and instantiate it into a practical framework. Building on this, we introduce Style-Conditioned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22823","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/2601.22823/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:17:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e+PI6AMNdaxasKopBP6bobRA5NTOAms83mIKZksH9Vwcov5lpwT3XCWZcU1RmGRP/lpSYeH2cTm+WIkmTyqeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:15:33.440752Z"},"content_sha256":"a7574e52121d29f119032906feea8298701c99477ccc07cfda7e3516da33f3d7","schema_version":"1.0","event_id":"sha256:a7574e52121d29f119032906feea8298701c99477ccc07cfda7e3516da33f3d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5MK3DEVQMN47Z6BK5IGJULANEI/bundle.json","state_url":"https://pith.science/pith/5MK3DEVQMN47Z6BK5IGJULANEI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5MK3DEVQMN47Z6BK5IGJULANEI/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":"2026-07-13T00:15:33Z","links":{"resolver":"https://pith.science/pith/5MK3DEVQMN47Z6BK5IGJULANEI","bundle":"https://pith.science/pith/5MK3DEVQMN47Z6BK5IGJULANEI/bundle.json","state":"https://pith.science/pith/5MK3DEVQMN47Z6BK5IGJULANEI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5MK3DEVQMN47Z6BK5IGJULANEI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5MK3DEVQMN47Z6BK5IGJULANEI","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":"bcf3177d0a6779640d152acfaa0c2cad84d4ad17889f3d9da4595214b53b2fa8","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T10:49:22Z","title_canon_sha256":"444b53ca82e817acb064e970e5b223c5b15d970633e4bd2e6298973d23c7aac4"},"schema_version":"1.0","source":{"id":"2601.22823","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22823","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22823v2","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22823","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"5MK3DEVQMN47","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"5MK3DEVQMN47Z6BK","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"5MK3DEVQ","created_at":"2026-06-30T01:17:33Z"}],"graph_snapshots":[{"event_id":"sha256:a7574e52121d29f119032906feea8298701c99477ccc07cfda7e3516da33f3d7","target":"graph","created_at":"2026-06-30T01:17:33Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.22823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to distribution shift and inherent conflicts between style and reward. Existing methods, despite introducing numerous definitions of style, often fail to reconcile these objectives effectively. To address these challenges, we propose a unified definition of behavior style and instantiate it into a practical framework. Building on this, we introduce Style-Conditioned","authors_text":"Mathieu Petitbois, R\\'emy Portelas, Sylvain Lamprier","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T10:49:22Z","title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22823","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:095021bce9c6cf32f07e3f237ceaf87208db878c438f77dd606f46dc9ef8c9ec","target":"record","created_at":"2026-06-30T01:17:33Z","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":"bcf3177d0a6779640d152acfaa0c2cad84d4ad17889f3d9da4595214b53b2fa8","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T10:49:22Z","title_canon_sha256":"444b53ca82e817acb064e970e5b223c5b15d970633e4bd2e6298973d23c7aac4"},"schema_version":"1.0","source":{"id":"2601.22823","kind":"arxiv","version":2}},"canonical_sha256":"eb15b192b06379fcf82aea0c9a2c0d222de62dafc643971872da51f4d2de8fdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb15b192b06379fcf82aea0c9a2c0d222de62dafc643971872da51f4d2de8fdf","first_computed_at":"2026-06-30T01:17:33.299875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:33.299875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UkVj9K9z7aUXITpDo08TzDxYWt32HpY9KePUaV1dM2cSc9YGiuTraq0PUcAvgXoVx6w5ucWD87+aH6fizWL+Cw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:33.300694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.22823","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:095021bce9c6cf32f07e3f237ceaf87208db878c438f77dd606f46dc9ef8c9ec","sha256:a7574e52121d29f119032906feea8298701c99477ccc07cfda7e3516da33f3d7"],"state_sha256":"764f270c3e899b8ef41d12574a80441f7f6b075ed9139c43bdd7e9460bc91674"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iv4G1UcDmE6mSz5cfDOp9cmPXKXbVknwwDJZW/1qwBWRyg349PPMi4TQVYo+Y7+ITez5OHuK7s4ffGkxoD3gAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T00:15:33.444707Z","bundle_sha256":"d35a86cfde85268383e8a30753a7f1547add87253f39fdb9ab6e36618cc300b3"}}