{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IWCLOPNMGBZOHMTE4IEYLC3RJE","short_pith_number":"pith:IWCLOPNM","canonical_record":{"source":{"id":"2501.01544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T21:31:38Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"09b595c2ddf58bd191e848fdc2835e8ebf8cb7867796cbf9475174bb0ba658e1","abstract_canon_sha256":"b65706f711c1e249a09946734d9926037911913fae7657afee547ede30076529"},"schema_version":"1.0"},"canonical_sha256":"4584b73dac3072e3b264e209858b714922d3c658c60bbe2cb08093ce91372f83","source":{"kind":"arxiv","id":"2501.01544","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01544","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01544v1","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01544","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"IWCLOPNMGBZO","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"IWCLOPNMGBZOHMTE","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"IWCLOPNM","created_at":"2026-07-05T09:56:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IWCLOPNMGBZOHMTE4IEYLC3RJE","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T21:31:38Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"09b595c2ddf58bd191e848fdc2835e8ebf8cb7867796cbf9475174bb0ba658e1","abstract_canon_sha256":"b65706f711c1e249a09946734d9926037911913fae7657afee547ede30076529"},"schema_version":"1.0"},"canonical_sha256":"4584b73dac3072e3b264e209858b714922d3c658c60bbe2cb08093ce91372f83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:26.447609Z","signature_b64":"16PeO3akyzLTDueDmzlbWV8P3ha8LmQSjahFZ+J9aaEemhxgVBGBJRzNPMEjvXgKNTspbEwpm/Aqx2EY5ACjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4584b73dac3072e3b264e209858b714922d3c658c60bbe2cb08093ce91372f83","last_reissued_at":"2026-07-05T09:56:26.447133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:26.447133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01544","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":"2026-07-05T09:56:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8Ro4U2JfPL6S/5WVhacJoUtxss3720MyoT/YcSt7fV4sqG62AkfJKFl5rW/YCw/xb143+FOZXFB2fWovh91DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:37:05.079522Z"},"content_sha256":"4681947dea683ab6bfda14f653ad7d7bd88f1d5a5802c6fbed8a822323a09f0b","schema_version":"1.0","event_id":"sha256:4681947dea683ab6bfda14f653ad7d7bd88f1d5a5802c6fbed8a822323a09f0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IWCLOPNMGBZOHMTE4IEYLC3RJE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antoine Grosnit, Haitham Bou-Ammar, Rasul Tutnov","submitted_at":"2025-01-02T21:31:38Z","abstract_excerpt":"Post-alignment of large language models (LLMs) is critical in improving their utility, safety, and alignment with human intentions. Direct preference optimisation (DPO) has become one of the most widely used algorithms for achieving this alignment, given its ability to optimise models based on human feedback directly. However, the vast number of DPO variants in the literature has made it increasingly difficult for researchers to navigate and fully grasp the connections between these approaches. This paper introduces a unifying framework inspired by mutual information, which proposes a new loss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01544","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/2501.01544/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":"2026-07-05T09:56:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYSIc57+/+rp4mTMTnwefs/wN255wjbClcnKiAXdMKkdG479UnNTzYKFrH7b0e6uo20xlVGS86Tt/0jnaaMfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:37:05.080033Z"},"content_sha256":"1e6d86cc9b8dc2ea2dcedfe5f527912bdd7225b836ac147a8de8cb4569d4280e","schema_version":"1.0","event_id":"sha256:1e6d86cc9b8dc2ea2dcedfe5f527912bdd7225b836ac147a8de8cb4569d4280e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWCLOPNMGBZOHMTE4IEYLC3RJE/bundle.json","state_url":"https://pith.science/pith/IWCLOPNMGBZOHMTE4IEYLC3RJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWCLOPNMGBZOHMTE4IEYLC3RJE/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":"2026-08-23T19:37:05Z","links":{"resolver":"https://pith.science/pith/IWCLOPNMGBZOHMTE4IEYLC3RJE","bundle":"https://pith.science/pith/IWCLOPNMGBZOHMTE4IEYLC3RJE/bundle.json","state":"https://pith.science/pith/IWCLOPNMGBZOHMTE4IEYLC3RJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWCLOPNMGBZOHMTE4IEYLC3RJE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IWCLOPNMGBZOHMTE4IEYLC3RJE","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":"b65706f711c1e249a09946734d9926037911913fae7657afee547ede30076529","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T21:31:38Z","title_canon_sha256":"09b595c2ddf58bd191e848fdc2835e8ebf8cb7867796cbf9475174bb0ba658e1"},"schema_version":"1.0","source":{"id":"2501.01544","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01544","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01544v1","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01544","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"IWCLOPNMGBZO","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"IWCLOPNMGBZOHMTE","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"IWCLOPNM","created_at":"2026-07-05T09:56:26Z"}],"graph_snapshots":[{"event_id":"sha256:1e6d86cc9b8dc2ea2dcedfe5f527912bdd7225b836ac147a8de8cb4569d4280e","target":"graph","created_at":"2026-07-05T09:56:26Z","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/2501.01544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-alignment of large language models (LLMs) is critical in improving their utility, safety, and alignment with human intentions. Direct preference optimisation (DPO) has become one of the most widely used algorithms for achieving this alignment, given its ability to optimise models based on human feedback directly. However, the vast number of DPO variants in the literature has made it increasingly difficult for researchers to navigate and fully grasp the connections between these approaches. This paper introduces a unifying framework inspired by mutual information, which proposes a new loss","authors_text":"Antoine Grosnit, Haitham Bou-Ammar, Rasul Tutnov","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T21:31:38Z","title":"Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01544","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":"sha256:4681947dea683ab6bfda14f653ad7d7bd88f1d5a5802c6fbed8a822323a09f0b","target":"record","created_at":"2026-07-05T09:56:26Z","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":"b65706f711c1e249a09946734d9926037911913fae7657afee547ede30076529","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T21:31:38Z","title_canon_sha256":"09b595c2ddf58bd191e848fdc2835e8ebf8cb7867796cbf9475174bb0ba658e1"},"schema_version":"1.0","source":{"id":"2501.01544","kind":"arxiv","version":1}},"canonical_sha256":"4584b73dac3072e3b264e209858b714922d3c658c60bbe2cb08093ce91372f83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4584b73dac3072e3b264e209858b714922d3c658c60bbe2cb08093ce91372f83","first_computed_at":"2026-07-05T09:56:26.447133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:26.447133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"16PeO3akyzLTDueDmzlbWV8P3ha8LmQSjahFZ+J9aaEemhxgVBGBJRzNPMEjvXgKNTspbEwpm/Aqx2EY5ACjDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:26.447609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01544","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4681947dea683ab6bfda14f653ad7d7bd88f1d5a5802c6fbed8a822323a09f0b","sha256:1e6d86cc9b8dc2ea2dcedfe5f527912bdd7225b836ac147a8de8cb4569d4280e"],"state_sha256":"e8b03f07ca0d5254d38b6c65175578ac65777f2c24f86f94091b7864870efaf5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tr3TWOq6s0Y7V07NbfZDyHE3pehZ9W6XD9VZKea/BlgHiXpj45VKjljoDiRH9uD8LpkRSttu0OlDmAC1tDFhCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T19:37:05.084308Z","bundle_sha256":"cad63a39505ac4116ade6d9907011d8f789a40fe433c16cd9ab5ed71422a4226"}}