{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JMVPWCFNZX2FJ2SB3FF3KD6OZ6","short_pith_number":"pith:JMVPWCFN","canonical_record":{"source":{"id":"2606.12881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T04:15:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1837fea65420d83284d2e77e742a5aafa2a6c30eb82046094e35a0dd34114558","abstract_canon_sha256":"02316652f8764e048634be42e2af5ff22aa378a7ce8f922a76e913f44d261e67"},"schema_version":"1.0"},"canonical_sha256":"4b2afb08adcdf454ea41d94bb50fcecfbd2f82ebf277815360bbf5ddb8e03c6a","source":{"kind":"arxiv","id":"2606.12881","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12881","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12881v1","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12881","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"JMVPWCFNZX2F","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"JMVPWCFNZX2FJ2SB","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"JMVPWCFN","created_at":"2026-06-12T01:08:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JMVPWCFNZX2FJ2SB3FF3KD6OZ6","target":"record","payload":{"canonical_record":{"source":{"id":"2606.12881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T04:15:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1837fea65420d83284d2e77e742a5aafa2a6c30eb82046094e35a0dd34114558","abstract_canon_sha256":"02316652f8764e048634be42e2af5ff22aa378a7ce8f922a76e913f44d261e67"},"schema_version":"1.0"},"canonical_sha256":"4b2afb08adcdf454ea41d94bb50fcecfbd2f82ebf277815360bbf5ddb8e03c6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:56.488921Z","signature_b64":"sD0WM6quHsyOHP3KBoIyQofrh5FEMQACQCv9Py08/oEVR9MvqtBJcCVLwKZVlQwSwu59nzjh9dzH4nplSbpCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b2afb08adcdf454ea41d94bb50fcecfbd2f82ebf277815360bbf5ddb8e03c6a","last_reissued_at":"2026-06-12T01:08:56.488148Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:56.488148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.12881","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":"2026-06-12T01:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+MyOobwD+zwovt6AEWRHxLDRlYETFF46nkedP3NAhndaiDGixzxTuX77VDusXDO0rTV37KoOWO9yTFwehfdMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:33:48.007173Z"},"content_sha256":"bdbdb22342c5b2d4309db6af992e0d42ac78b7a993bd4dd45d9edeb7870f4fc4","schema_version":"1.0","event_id":"sha256:bdbdb22342c5b2d4309db6af992e0d42ac78b7a993bd4dd45d9edeb7870f4fc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JMVPWCFNZX2FJ2SB3FF3KD6OZ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dezhi YU, ShuoJia Fu, Yvonne Qiu","submitted_at":"2026-06-11T04:15:54Z","abstract_excerpt":"We present an approach to fine-tuning large language models using Direct Preference Optimization (DPO), a reinforcement learning technique. Our experimental results demonstrate that DPO simplifies the training pipeline, improves computational efficiency, and achieves competitive performance. The evaluation using BLEU, ROUGE, and cosine similarity metrics indicates effective learning and convergence, though further investigation is needed to address observed training instability."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12881","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/2606.12881/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":"2026-06-12T01:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDl3WjQra+K+oG9+FDI+E0lv1UQ6F3VAscoWGnXASr5GrgSmA6X3F52moCLAw1yjKTi+Y9FmAiHYEV6Lu+2vBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:33:48.008516Z"},"content_sha256":"cdad2be000d12447b919e7c4a8e793b798ace17ad69b2f13a8d9f2d00cbe7ed2","schema_version":"1.0","event_id":"sha256:cdad2be000d12447b919e7c4a8e793b798ace17ad69b2f13a8d9f2d00cbe7ed2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMVPWCFNZX2FJ2SB3FF3KD6OZ6/bundle.json","state_url":"https://pith.science/pith/JMVPWCFNZX2FJ2SB3FF3KD6OZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMVPWCFNZX2FJ2SB3FF3KD6OZ6/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":"2026-08-14T13:33:48Z","links":{"resolver":"https://pith.science/pith/JMVPWCFNZX2FJ2SB3FF3KD6OZ6","bundle":"https://pith.science/pith/JMVPWCFNZX2FJ2SB3FF3KD6OZ6/bundle.json","state":"https://pith.science/pith/JMVPWCFNZX2FJ2SB3FF3KD6OZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMVPWCFNZX2FJ2SB3FF3KD6OZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JMVPWCFNZX2FJ2SB3FF3KD6OZ6","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":"02316652f8764e048634be42e2af5ff22aa378a7ce8f922a76e913f44d261e67","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T04:15:54Z","title_canon_sha256":"1837fea65420d83284d2e77e742a5aafa2a6c30eb82046094e35a0dd34114558"},"schema_version":"1.0","source":{"id":"2606.12881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12881","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12881v1","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12881","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"JMVPWCFNZX2F","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"JMVPWCFNZX2FJ2SB","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"JMVPWCFN","created_at":"2026-06-12T01:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:cdad2be000d12447b919e7c4a8e793b798ace17ad69b2f13a8d9f2d00cbe7ed2","target":"graph","created_at":"2026-06-12T01:08:56Z","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/2606.12881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an approach to fine-tuning large language models using Direct Preference Optimization (DPO), a reinforcement learning technique. Our experimental results demonstrate that DPO simplifies the training pipeline, improves computational efficiency, and achieves competitive performance. The evaluation using BLEU, ROUGE, and cosine similarity metrics indicates effective learning and convergence, though further investigation is needed to address observed training instability.","authors_text":"Dezhi YU, ShuoJia Fu, Yvonne Qiu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T04:15:54Z","title":"Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12881","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:bdbdb22342c5b2d4309db6af992e0d42ac78b7a993bd4dd45d9edeb7870f4fc4","target":"record","created_at":"2026-06-12T01:08:56Z","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":"02316652f8764e048634be42e2af5ff22aa378a7ce8f922a76e913f44d261e67","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T04:15:54Z","title_canon_sha256":"1837fea65420d83284d2e77e742a5aafa2a6c30eb82046094e35a0dd34114558"},"schema_version":"1.0","source":{"id":"2606.12881","kind":"arxiv","version":1}},"canonical_sha256":"4b2afb08adcdf454ea41d94bb50fcecfbd2f82ebf277815360bbf5ddb8e03c6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b2afb08adcdf454ea41d94bb50fcecfbd2f82ebf277815360bbf5ddb8e03c6a","first_computed_at":"2026-06-12T01:08:56.488148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:56.488148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sD0WM6quHsyOHP3KBoIyQofrh5FEMQACQCv9Py08/oEVR9MvqtBJcCVLwKZVlQwSwu59nzjh9dzH4nplSbpCDw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:56.488921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdbdb22342c5b2d4309db6af992e0d42ac78b7a993bd4dd45d9edeb7870f4fc4","sha256:cdad2be000d12447b919e7c4a8e793b798ace17ad69b2f13a8d9f2d00cbe7ed2"],"state_sha256":"c1838507f7c85ec1c0f1b7d3e4c69bb7703597f79540b129bad32fb0bfce0c4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Z3P7HEM4N20Oh570YBWM3HUsA1wCKHI1Hsgfp3/lWS8YYeCQTTJBv67w+D7Nmb5R1lgfWEzXoGLAhj6E2b9Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:33:48.013787Z","bundle_sha256":"769fd6cb7cc8c896003d89a6a7a0c08b704ea76fc9ffaf426ef9934c0bed6f68"}}