{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O6PD75NUVVYELB2PRVOAZULQGN","short_pith_number":"pith:O6PD75NU","canonical_record":{"source":{"id":"2506.12529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:01:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bc309420d9cc02962384f829a357d4299213867966c99fc863b0dbcbe10823d5","abstract_canon_sha256":"30b356cc32bab2f795881cc56da4c799153b112c32cd89ca8f4b113812c804d2"},"schema_version":"1.0"},"canonical_sha256":"779e3ff5b4ad7045874f8d5c0cd1703375b4db2f5d71f53282974c498bbca745","source":{"kind":"arxiv","id":"2506.12529","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12529","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12529v1","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12529","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"O6PD75NUVVYE","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"O6PD75NUVVYELB2P","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"O6PD75NU","created_at":"2026-07-05T11:21:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O6PD75NUVVYELB2PRVOAZULQGN","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:01:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bc309420d9cc02962384f829a357d4299213867966c99fc863b0dbcbe10823d5","abstract_canon_sha256":"30b356cc32bab2f795881cc56da4c799153b112c32cd89ca8f4b113812c804d2"},"schema_version":"1.0"},"canonical_sha256":"779e3ff5b4ad7045874f8d5c0cd1703375b4db2f5d71f53282974c498bbca745","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:54.797689Z","signature_b64":"55gMXz01Auj4r4+7X5sMT8DF6j2gwwJudNHJnW+V5ky+77G5y/YZ+d5QhhmpZmqPUuGZFpn/rRfiQ19gm5k4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"779e3ff5b4ad7045874f8d5c0cd1703375b4db2f5d71f53282974c498bbca745","last_reissued_at":"2026-07-05T11:21:54.797276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:54.797276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12529","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"os79H8quihuOLCsuWUu1n+SZSTJ6g2SL5qMfBGp1BfrvDAfRQyWf+YY99C1QbroOuENVvw7lDl9X1oGZjlerCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:48:03.593132Z"},"content_sha256":"489302ce8017694e7279cdc8f9d348ef4c7c9ae1b787ff20f6bef6e34c4c76c0","schema_version":"1.0","event_id":"sha256:489302ce8017694e7279cdc8f9d348ef4c7c9ae1b787ff20f6bef6e34c4c76c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O6PD75NUVVYELB2PRVOAZULQGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabian H. Sinz, R. James Cotton, Sara Rajaram","submitted_at":"2025-06-14T15:01:59Z","abstract_excerpt":"Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering. However, most previous PbRL work has not investigated the robustness to labeler errors, inevitable with labelers who are non-experts or operate under time constraints. Additionally, PbRL algorithms often target very specific settings (e.g. pairwise ranked preferences or purely offline learning). We introduce Similarity as Reward Alignment (SARA), a simple contrastive framework that is both resilient to noisy labels and adaptable to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12529","kind":"arxiv","version":1},"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/2506.12529/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":"2026-07-05T11:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MvOeT3WhSR1p3HKITcpjM0FKsIFc7g137dwYR6YNfZT1zf2Eg9KnVXOsFaiwwW2ksM6+X3oJpVof8hpSw/0LDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:48:03.594033Z"},"content_sha256":"bd88cba2a5c76ad92957e80cee23c80c9d14413bf0dfd29957da4143b0e43f45","schema_version":"1.0","event_id":"sha256:bd88cba2a5c76ad92957e80cee23c80c9d14413bf0dfd29957da4143b0e43f45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6PD75NUVVYELB2PRVOAZULQGN/bundle.json","state_url":"https://pith.science/pith/O6PD75NUVVYELB2PRVOAZULQGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6PD75NUVVYELB2PRVOAZULQGN/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":"2026-08-10T16:48:03Z","links":{"resolver":"https://pith.science/pith/O6PD75NUVVYELB2PRVOAZULQGN","bundle":"https://pith.science/pith/O6PD75NUVVYELB2PRVOAZULQGN/bundle.json","state":"https://pith.science/pith/O6PD75NUVVYELB2PRVOAZULQGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6PD75NUVVYELB2PRVOAZULQGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O6PD75NUVVYELB2PRVOAZULQGN","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":"30b356cc32bab2f795881cc56da4c799153b112c32cd89ca8f4b113812c804d2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:01:59Z","title_canon_sha256":"bc309420d9cc02962384f829a357d4299213867966c99fc863b0dbcbe10823d5"},"schema_version":"1.0","source":{"id":"2506.12529","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12529","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12529v1","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12529","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"O6PD75NUVVYE","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"O6PD75NUVVYELB2P","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"O6PD75NU","created_at":"2026-07-05T11:21:54Z"}],"graph_snapshots":[{"event_id":"sha256:bd88cba2a5c76ad92957e80cee23c80c9d14413bf0dfd29957da4143b0e43f45","target":"graph","created_at":"2026-07-05T11:21:54Z","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/2506.12529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering. However, most previous PbRL work has not investigated the robustness to labeler errors, inevitable with labelers who are non-experts or operate under time constraints. Additionally, PbRL algorithms often target very specific settings (e.g. pairwise ranked preferences or purely offline learning). We introduce Similarity as Reward Alignment (SARA), a simple contrastive framework that is both resilient to noisy labels and adaptable to ","authors_text":"Fabian H. Sinz, R. James Cotton, Sara Rajaram","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:01:59Z","title":"Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12529","kind":"arxiv","version":1},"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":"sha256:489302ce8017694e7279cdc8f9d348ef4c7c9ae1b787ff20f6bef6e34c4c76c0","target":"record","created_at":"2026-07-05T11:21:54Z","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":"30b356cc32bab2f795881cc56da4c799153b112c32cd89ca8f4b113812c804d2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:01:59Z","title_canon_sha256":"bc309420d9cc02962384f829a357d4299213867966c99fc863b0dbcbe10823d5"},"schema_version":"1.0","source":{"id":"2506.12529","kind":"arxiv","version":1}},"canonical_sha256":"779e3ff5b4ad7045874f8d5c0cd1703375b4db2f5d71f53282974c498bbca745","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"779e3ff5b4ad7045874f8d5c0cd1703375b4db2f5d71f53282974c498bbca745","first_computed_at":"2026-07-05T11:21:54.797276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:54.797276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"55gMXz01Auj4r4+7X5sMT8DF6j2gwwJudNHJnW+V5ky+77G5y/YZ+d5QhhmpZmqPUuGZFpn/rRfiQ19gm5k4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:54.797689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12529","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:489302ce8017694e7279cdc8f9d348ef4c7c9ae1b787ff20f6bef6e34c4c76c0","sha256:bd88cba2a5c76ad92957e80cee23c80c9d14413bf0dfd29957da4143b0e43f45"],"state_sha256":"ff34d852c52f992924753d14745049470fd78dfbcd4ebc142c626dc7a6c1c687"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QwLdyFI7DWJnX8h10RwU8cQ1Zlk2NomP5CcnH+cmmFDojZyCVvFn0hBXz10WxfVB7UZse3H24695YaQBz5sCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:48:03.599977Z","bundle_sha256":"97f12f27556a661eed698b51f4c43d8d4ef0db69fab46cfb7b0764aec90a0d42"}}