{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QFIYMMFQXZUNLUVREQVGGFWBIX","short_pith_number":"pith:QFIYMMFQ","canonical_record":{"source":{"id":"2409.13683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T17:51:24Z","cross_cats_sorted":[],"title_canon_sha256":"62408f1b2c9b2d2c770b0be95eeb00c095c0b7970784f37401574963466e1cf4","abstract_canon_sha256":"4b46816f2ab3cbbd84618a905286df9648f9b75c7de2b715ce9db60bbb71b655"},"schema_version":"1.0"},"canonical_sha256":"81518630b0be68d5d2b1242a6316c145c03a95c3a94945f047d970e3bdad6ba6","source":{"kind":"arxiv","id":"2409.13683","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13683","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13683v2","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13683","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_12","alias_value":"QFIYMMFQXZUN","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"QFIYMMFQXZUNLUVR","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"QFIYMMFQ","created_at":"2026-07-05T10:28:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QFIYMMFQXZUNLUVREQVGGFWBIX","target":"record","payload":{"canonical_record":{"source":{"id":"2409.13683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T17:51:24Z","cross_cats_sorted":[],"title_canon_sha256":"62408f1b2c9b2d2c770b0be95eeb00c095c0b7970784f37401574963466e1cf4","abstract_canon_sha256":"4b46816f2ab3cbbd84618a905286df9648f9b75c7de2b715ce9db60bbb71b655"},"schema_version":"1.0"},"canonical_sha256":"81518630b0be68d5d2b1242a6316c145c03a95c3a94945f047d970e3bdad6ba6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:22.147322Z","signature_b64":"TktQStSHFeK+2Vj9RD7mNasbSRce3LxxO/aWMVrREMdl8jUzuSenlBq1FjB01c5hTfIHGqnF9Ir175GfoYk9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81518630b0be68d5d2b1242a6316c145c03a95c3a94945f047d970e3bdad6ba6","last_reissued_at":"2026-07-05T10:28:22.146865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:22.146865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.13683","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":"2026-07-05T10:28:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YMwjjqy9NHshXDW9/khpPfIgbN95rzAjso43oz+9K0F6+sx/W/Co4oIuNH7IKUtgpcU4gyDCvkXdHzdVZDGiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:57:05.200867Z"},"content_sha256":"13922bce3ff8d9e640e7598999991fdd246800d6d477268a05aa226163234030","schema_version":"1.0","event_id":"sha256:13922bce3ff8d9e640e7598999991fdd246800d6d477268a05aa226163234030"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QFIYMMFQXZUNLUVREQVGGFWBIX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PrefMMT: Modeling Human Preferences in Preference-based Reinforcement Learning with Multimodal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Byung-Cheol Min, Dayoon Suh, Dezhong Zhao, Guohua Chen, Ruiqi Wang, Taehyeon Kim, Ziqin Yuan","submitted_at":"2024-09-20T17:51:24Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) shows promise in aligning robot behaviors with human preferences, but its success depends heavily on the accurate modeling of human preferences through reward models. Most methods adopt Markovian assumptions for preference modeling (PM), which overlook the temporal dependencies within robot behavior trajectories that impact human evaluations. While recent works have utilized sequence modeling to mitigate this by learning sequential non-Markovian rewards, they ignore the multimodal nature of robot trajectories, which consist of elements from two di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13683","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/2409.13683/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":"2026-07-05T10:28:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+7IVwFjZYEbaAwRth0MLGR+TEq3a/Sly+Q+U/flFMqtzCZUwsl2TxaCGm8CCwxmFdnM8N1dN9LIQ7GPVSAjhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:57:05.201722Z"},"content_sha256":"5f850a8f12a682eb8d768769183311b07b7a34731fb3efb5a386080a481a69a9","schema_version":"1.0","event_id":"sha256:5f850a8f12a682eb8d768769183311b07b7a34731fb3efb5a386080a481a69a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFIYMMFQXZUNLUVREQVGGFWBIX/bundle.json","state_url":"https://pith.science/pith/QFIYMMFQXZUNLUVREQVGGFWBIX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFIYMMFQXZUNLUVREQVGGFWBIX/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":"2026-08-17T12:57:05Z","links":{"resolver":"https://pith.science/pith/QFIYMMFQXZUNLUVREQVGGFWBIX","bundle":"https://pith.science/pith/QFIYMMFQXZUNLUVREQVGGFWBIX/bundle.json","state":"https://pith.science/pith/QFIYMMFQXZUNLUVREQVGGFWBIX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFIYMMFQXZUNLUVREQVGGFWBIX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QFIYMMFQXZUNLUVREQVGGFWBIX","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":"4b46816f2ab3cbbd84618a905286df9648f9b75c7de2b715ce9db60bbb71b655","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T17:51:24Z","title_canon_sha256":"62408f1b2c9b2d2c770b0be95eeb00c095c0b7970784f37401574963466e1cf4"},"schema_version":"1.0","source":{"id":"2409.13683","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13683","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13683v2","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13683","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_12","alias_value":"QFIYMMFQXZUN","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"QFIYMMFQXZUNLUVR","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"QFIYMMFQ","created_at":"2026-07-05T10:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:5f850a8f12a682eb8d768769183311b07b7a34731fb3efb5a386080a481a69a9","target":"graph","created_at":"2026-07-05T10:28:22Z","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/2409.13683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) shows promise in aligning robot behaviors with human preferences, but its success depends heavily on the accurate modeling of human preferences through reward models. Most methods adopt Markovian assumptions for preference modeling (PM), which overlook the temporal dependencies within robot behavior trajectories that impact human evaluations. While recent works have utilized sequence modeling to mitigate this by learning sequential non-Markovian rewards, they ignore the multimodal nature of robot trajectories, which consist of elements from two di","authors_text":"Byung-Cheol Min, Dayoon Suh, Dezhong Zhao, Guohua Chen, Ruiqi Wang, Taehyeon Kim, Ziqin Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T17:51:24Z","title":"PrefMMT: Modeling Human Preferences in Preference-based Reinforcement Learning with Multimodal Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13683","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":"sha256:13922bce3ff8d9e640e7598999991fdd246800d6d477268a05aa226163234030","target":"record","created_at":"2026-07-05T10:28:22Z","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":"4b46816f2ab3cbbd84618a905286df9648f9b75c7de2b715ce9db60bbb71b655","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T17:51:24Z","title_canon_sha256":"62408f1b2c9b2d2c770b0be95eeb00c095c0b7970784f37401574963466e1cf4"},"schema_version":"1.0","source":{"id":"2409.13683","kind":"arxiv","version":2}},"canonical_sha256":"81518630b0be68d5d2b1242a6316c145c03a95c3a94945f047d970e3bdad6ba6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81518630b0be68d5d2b1242a6316c145c03a95c3a94945f047d970e3bdad6ba6","first_computed_at":"2026-07-05T10:28:22.146865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:22.146865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TktQStSHFeK+2Vj9RD7mNasbSRce3LxxO/aWMVrREMdl8jUzuSenlBq1FjB01c5hTfIHGqnF9Ir175GfoYk9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:22.147322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13683","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13922bce3ff8d9e640e7598999991fdd246800d6d477268a05aa226163234030","sha256:5f850a8f12a682eb8d768769183311b07b7a34731fb3efb5a386080a481a69a9"],"state_sha256":"0a797f0f330259b31101304d00ba057e99eacedc0735b19b28b7c65595a5d53c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zoS912fsE2bbc/kGgJIyXjfcjnCNEVVxlpqFcechlOP5Khy4wAvnjGwWYf/rWB3vF+fADQ4yteKp+g0gIi1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:57:05.275241Z","bundle_sha256":"56e898d363d139cf392458c43a770e52398ab6b234c4ff1531b2323505760dad"}}