{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DR5VM333ID4NDYCYTUMFLE3MPS","short_pith_number":"pith:DR5VM333","canonical_record":{"source":{"id":"2411.01493","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T09:18:28Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9f8c496f3593efb50c4a3dd65b80812229522042f831a6a20aa0fc066428ecce","abstract_canon_sha256":"772b2510cd6b769930664621d0571424808f985e74441c4dc2a3cac77a9a249d"},"schema_version":"1.0"},"canonical_sha256":"1c7b566f7b40f8d1e0589d1855936c7cac2e2365412fb8a1fccd8efc6415fd20","source":{"kind":"arxiv","id":"2411.01493","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01493","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01493v2","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01493","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"DR5VM333ID4N","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_16","alias_value":"DR5VM333ID4NDYCY","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_8","alias_value":"DR5VM333","created_at":"2026-07-05T09:33:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DR5VM333ID4NDYCYTUMFLE3MPS","target":"record","payload":{"canonical_record":{"source":{"id":"2411.01493","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T09:18:28Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9f8c496f3593efb50c4a3dd65b80812229522042f831a6a20aa0fc066428ecce","abstract_canon_sha256":"772b2510cd6b769930664621d0571424808f985e74441c4dc2a3cac77a9a249d"},"schema_version":"1.0"},"canonical_sha256":"1c7b566f7b40f8d1e0589d1855936c7cac2e2365412fb8a1fccd8efc6415fd20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:39.907600Z","signature_b64":"pC6hUp1+X/eBIbqG33NBO1gCooOXiLYs4Nw3IWqkw0ALEWiHR6QaNke2W/C3qi3nfrnUVm0Fzto8r5+SMzL2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c7b566f7b40f8d1e0589d1855936c7cac2e2365412fb8a1fccd8efc6415fd20","last_reissued_at":"2026-07-05T09:33:39.907202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:39.907202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.01493","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":"2026-07-05T09:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3UFCLExHiXPfADGmev3OENG+UG3/dSgRcoAw7SHOZeUQctwOiw12Q2tM8oWEZyjBwj1cXVGSp7sB5RYTefCDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:31:53.049075Z"},"content_sha256":"ba806363b9e31f3020dbd1c2881c8dc8dec6b484881705b1d775d4bbb7d4653d","schema_version":"1.0","event_id":"sha256:ba806363b9e31f3020dbd1c2881c8dc8dec6b484881705b1d775d4bbb7d4653d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DR5VM333ID4NDYCYTUMFLE3MPS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-Efficient Alignment for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Changyu Chen, Chao Du, Min Lin, Wee Sun Lee, Zichen Liu","submitted_at":"2024-11-03T09:18:28Z","abstract_excerpt":"We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation, subsuming recent paradigms such as online RLHF and online DPO, inherently quests for sample-efficient algorithms that incorporate online active exploration. Leveraging insights from bandit theory, we introduce a unified algorithm based on Thompson sampling and highlight its applications in two distinct LLM alignment scenarios. The practical agent that efficiently i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01493","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/2411.01493/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":"2026-07-05T09:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+6n/x4c2X6SBW0siibjmaoTw6bBCl5ZMZtrVi/dhYxQmhGd1O6FEPW+HDtfZU/lP/UEqAksQXu+MDF4rkenCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:31:53.049631Z"},"content_sha256":"a93eb70ca846ac6fa0735fa2a76c17729ac09c607401645ac0dc0548d054c685","schema_version":"1.0","event_id":"sha256:a93eb70ca846ac6fa0735fa2a76c17729ac09c607401645ac0dc0548d054c685"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DR5VM333ID4NDYCYTUMFLE3MPS/bundle.json","state_url":"https://pith.science/pith/DR5VM333ID4NDYCYTUMFLE3MPS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DR5VM333ID4NDYCYTUMFLE3MPS/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":"2026-08-10T04:31:53Z","links":{"resolver":"https://pith.science/pith/DR5VM333ID4NDYCYTUMFLE3MPS","bundle":"https://pith.science/pith/DR5VM333ID4NDYCYTUMFLE3MPS/bundle.json","state":"https://pith.science/pith/DR5VM333ID4NDYCYTUMFLE3MPS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DR5VM333ID4NDYCYTUMFLE3MPS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DR5VM333ID4NDYCYTUMFLE3MPS","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":"772b2510cd6b769930664621d0571424808f985e74441c4dc2a3cac77a9a249d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T09:18:28Z","title_canon_sha256":"9f8c496f3593efb50c4a3dd65b80812229522042f831a6a20aa0fc066428ecce"},"schema_version":"1.0","source":{"id":"2411.01493","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01493","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01493v2","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01493","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"DR5VM333ID4N","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_16","alias_value":"DR5VM333ID4NDYCY","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_8","alias_value":"DR5VM333","created_at":"2026-07-05T09:33:39Z"}],"graph_snapshots":[{"event_id":"sha256:a93eb70ca846ac6fa0735fa2a76c17729ac09c607401645ac0dc0548d054c685","target":"graph","created_at":"2026-07-05T09:33:39Z","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/2411.01493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation, subsuming recent paradigms such as online RLHF and online DPO, inherently quests for sample-efficient algorithms that incorporate online active exploration. Leveraging insights from bandit theory, we introduce a unified algorithm based on Thompson sampling and highlight its applications in two distinct LLM alignment scenarios. The practical agent that efficiently i","authors_text":"Changyu Chen, Chao Du, Min Lin, Wee Sun Lee, Zichen Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T09:18:28Z","title":"Sample-Efficient Alignment for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01493","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:ba806363b9e31f3020dbd1c2881c8dc8dec6b484881705b1d775d4bbb7d4653d","target":"record","created_at":"2026-07-05T09:33:39Z","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":"772b2510cd6b769930664621d0571424808f985e74441c4dc2a3cac77a9a249d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T09:18:28Z","title_canon_sha256":"9f8c496f3593efb50c4a3dd65b80812229522042f831a6a20aa0fc066428ecce"},"schema_version":"1.0","source":{"id":"2411.01493","kind":"arxiv","version":2}},"canonical_sha256":"1c7b566f7b40f8d1e0589d1855936c7cac2e2365412fb8a1fccd8efc6415fd20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c7b566f7b40f8d1e0589d1855936c7cac2e2365412fb8a1fccd8efc6415fd20","first_computed_at":"2026-07-05T09:33:39.907202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:39.907202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pC6hUp1+X/eBIbqG33NBO1gCooOXiLYs4Nw3IWqkw0ALEWiHR6QaNke2W/C3qi3nfrnUVm0Fzto8r5+SMzL2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:39.907600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01493","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba806363b9e31f3020dbd1c2881c8dc8dec6b484881705b1d775d4bbb7d4653d","sha256:a93eb70ca846ac6fa0735fa2a76c17729ac09c607401645ac0dc0548d054c685"],"state_sha256":"6ee90f28002bfd8b5d384fff01ecc71fdcfa291ea96e7d818814a1ce40b55b19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"suQJfQpqpVaChkXxpYjRxF/2sZq+30WwGgDKVFfLEWT3UgIMpfb5G3pRXYqMELinkjjG6sOc3wImuhLayeeZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:31:53.053454Z","bundle_sha256":"8a74ca212d4a3c6848615b091479fb2a0560541ad040fa9467324d34fa183b55"}}