{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ML636A24BKPIY7GTD5XNNH53NO","short_pith_number":"pith:ML636A24","canonical_record":{"source":{"id":"2312.02554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T07:52:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"82532e247b97ea5869826be6ed48a63d5701c87f1443d6b62d84d7767fe91068","abstract_canon_sha256":"f9ad7e2e6c301d86a6f4b57c7782bdf778c610037bfe12f010f8c219bef98339"},"schema_version":"1.0"},"canonical_sha256":"62fdbf035c0a9e8c7cd31f6ed69fbb6b8cd713e7f26b9ce001ab1af246bcddc2","source":{"kind":"arxiv","id":"2312.02554","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02554","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02554v2","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02554","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"pith_short_12","alias_value":"ML636A24BKPI","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"pith_short_16","alias_value":"ML636A24BKPIY7GT","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"pith_short_8","alias_value":"ML636A24","created_at":"2026-07-05T07:49:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ML636A24BKPIY7GTD5XNNH53NO","target":"record","payload":{"canonical_record":{"source":{"id":"2312.02554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T07:52:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"82532e247b97ea5869826be6ed48a63d5701c87f1443d6b62d84d7767fe91068","abstract_canon_sha256":"f9ad7e2e6c301d86a6f4b57c7782bdf778c610037bfe12f010f8c219bef98339"},"schema_version":"1.0"},"canonical_sha256":"62fdbf035c0a9e8c7cd31f6ed69fbb6b8cd713e7f26b9ce001ab1af246bcddc2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:16.636775Z","signature_b64":"IpPxYvsns23uX4AFsM31tShZwjksaBu16OgXubm0hlXzRiNC8Ia+yCmb0wjHyrIyk9kxI4rAX/CnbThNSAPwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62fdbf035c0a9e8c7cd31f6ed69fbb6b8cd713e7f26b9ce001ab1af246bcddc2","last_reissued_at":"2026-07-05T07:49:16.636350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:16.636350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.02554","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":"2026-07-05T07:49:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6RuZMshhMEc07G4Wd/fHkrYIm5qZCfX60BzJdkpaUASgE9R81jJD296TduuNPszuAHo4JPHlvGi5q96coX3qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:16:29.259463Z"},"content_sha256":"86d89cea5ebb781f017c82d91b1fe85319ae5bf783677969289b3cbfa792bf0c","schema_version":"1.0","event_id":"sha256:86d89cea5ebb781f017c82d91b1fe85319ae5bf783677969289b3cbfa792bf0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ML636A24BKPIY7GTD5XNNH53NO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Fei Teng, Guannan Zhang, Jinjie Gu, Jiyan Jiang, Tianchi Cai, Xierui Song","submitted_at":"2023-12-05T07:52:12Z","abstract_excerpt":"Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists of supervised fine-tuning and preference learning. Most preference learning methods, such as RLHF and DPO, depend on pairwise preference data, which inadequately address scenarios where human feedback is point-wise, leading to potential information loss and suboptimal performance. Addressing this gap, we introduce Point-wise Direct Preference Optimization, a novel preference learning method designed to harness point-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02554","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/2312.02554/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":"2026-07-05T07:49:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"teJ7oyUXy2Ny0qflX07fA8G7FzGKF2IB4/U2emtTwdkzhjSnY64suNfr2p5yBw7dd0+EHACYZPgt3sbCvltKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:16:29.259767Z"},"content_sha256":"de29673dd70264d9a7f95e1d03d0c3977cbeda722e7d558f4c51d684bbba23c1","schema_version":"1.0","event_id":"sha256:de29673dd70264d9a7f95e1d03d0c3977cbeda722e7d558f4c51d684bbba23c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ML636A24BKPIY7GTD5XNNH53NO/bundle.json","state_url":"https://pith.science/pith/ML636A24BKPIY7GTD5XNNH53NO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ML636A24BKPIY7GTD5XNNH53NO/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":"2026-07-31T15:16:29Z","links":{"resolver":"https://pith.science/pith/ML636A24BKPIY7GTD5XNNH53NO","bundle":"https://pith.science/pith/ML636A24BKPIY7GTD5XNNH53NO/bundle.json","state":"https://pith.science/pith/ML636A24BKPIY7GTD5XNNH53NO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ML636A24BKPIY7GTD5XNNH53NO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ML636A24BKPIY7GTD5XNNH53NO","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":"f9ad7e2e6c301d86a6f4b57c7782bdf778c610037bfe12f010f8c219bef98339","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T07:52:12Z","title_canon_sha256":"82532e247b97ea5869826be6ed48a63d5701c87f1443d6b62d84d7767fe91068"},"schema_version":"1.0","source":{"id":"2312.02554","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02554","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02554v2","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02554","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"pith_short_12","alias_value":"ML636A24BKPI","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"pith_short_16","alias_value":"ML636A24BKPIY7GT","created_at":"2026-07-05T07:49:16Z"},{"alias_kind":"pith_short_8","alias_value":"ML636A24","created_at":"2026-07-05T07:49:16Z"}],"graph_snapshots":[{"event_id":"sha256:de29673dd70264d9a7f95e1d03d0c3977cbeda722e7d558f4c51d684bbba23c1","target":"graph","created_at":"2026-07-05T07:49:16Z","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/2312.02554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists of supervised fine-tuning and preference learning. Most preference learning methods, such as RLHF and DPO, depend on pairwise preference data, which inadequately address scenarios where human feedback is point-wise, leading to potential information loss and suboptimal performance. Addressing this gap, we introduce Point-wise Direct Preference Optimization, a novel preference learning method designed to harness point-","authors_text":"Fei Teng, Guannan Zhang, Jinjie Gu, Jiyan Jiang, Tianchi Cai, Xierui Song","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T07:52:12Z","title":"ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02554","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":"sha256:86d89cea5ebb781f017c82d91b1fe85319ae5bf783677969289b3cbfa792bf0c","target":"record","created_at":"2026-07-05T07:49:16Z","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":"f9ad7e2e6c301d86a6f4b57c7782bdf778c610037bfe12f010f8c219bef98339","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T07:52:12Z","title_canon_sha256":"82532e247b97ea5869826be6ed48a63d5701c87f1443d6b62d84d7767fe91068"},"schema_version":"1.0","source":{"id":"2312.02554","kind":"arxiv","version":2}},"canonical_sha256":"62fdbf035c0a9e8c7cd31f6ed69fbb6b8cd713e7f26b9ce001ab1af246bcddc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62fdbf035c0a9e8c7cd31f6ed69fbb6b8cd713e7f26b9ce001ab1af246bcddc2","first_computed_at":"2026-07-05T07:49:16.636350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:16.636350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IpPxYvsns23uX4AFsM31tShZwjksaBu16OgXubm0hlXzRiNC8Ia+yCmb0wjHyrIyk9kxI4rAX/CnbThNSAPwBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:16.636775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02554","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86d89cea5ebb781f017c82d91b1fe85319ae5bf783677969289b3cbfa792bf0c","sha256:de29673dd70264d9a7f95e1d03d0c3977cbeda722e7d558f4c51d684bbba23c1"],"state_sha256":"37d892a466223a8b075d41863af8936af8cf43054dbf15b37cabbf7e96daec1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T81k0fJgsJgfKbe2NUdzPzm66qSMcu1RPNesf3v9uo/dypetb05+CRBnFAQhght+JMISoYwUf1HB8U18Lw/MAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T15:16:29.263054Z","bundle_sha256":"96584670dd5e2d536a14a411745ce8ab1a1f7b185bc8d65ad4fd26dadc42e8e5"}}