{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4XPIADPHVG7MOA4DBHZH4IW6N3","short_pith_number":"pith:4XPIADPH","canonical_record":{"source":{"id":"2504.07856","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T15:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"12c04a50f9d9ad7bddd82583df969420a0f0c4c69d88274c17d2e9ce1ef01881","abstract_canon_sha256":"4270507560a4329935ab2ff6740e280b19d9d6b19ea57750dbe91eed149d1c53"},"schema_version":"1.0"},"canonical_sha256":"e5de800de7a9bec7038309f27e22de6efe3994f11501fa34844f70218996e485","source":{"kind":"arxiv","id":"2504.07856","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07856","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07856v3","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07856","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"4XPIADPHVG7M","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_16","alias_value":"4XPIADPHVG7MOA4D","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_8","alias_value":"4XPIADPH","created_at":"2026-07-05T11:44:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4XPIADPHVG7MOA4DBHZH4IW6N3","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07856","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T15:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"12c04a50f9d9ad7bddd82583df969420a0f0c4c69d88274c17d2e9ce1ef01881","abstract_canon_sha256":"4270507560a4329935ab2ff6740e280b19d9d6b19ea57750dbe91eed149d1c53"},"schema_version":"1.0"},"canonical_sha256":"e5de800de7a9bec7038309f27e22de6efe3994f11501fa34844f70218996e485","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:47.659872Z","signature_b64":"eJ6+y/wsio0RrUtUlg78HOBCpmyo1Kk2WxQCV0uP/NJjD0TKdtK16k7k6FdyAQbySqT7QetPBeHESoLrN40gDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5de800de7a9bec7038309f27e22de6efe3994f11501fa34844f70218996e485","last_reissued_at":"2026-07-05T11:44:47.659395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:47.659395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07856","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Z1whx1sh5y+xswCtWMbtzs7m+4M9JjPR5xBgjMfQLRuMMDaWcpE2qJngZ8F2iTNmcURkhuhnYjTfEa7cJCDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:48:08.519425Z"},"content_sha256":"a507fa71bf363e99d7a571d08e6c68c06d47fa8633ea45a8484ec47b42c3091b","schema_version":"1.0","event_id":"sha256:a507fa71bf363e99d7a571d08e6c68c06d47fa8633ea45a8484ec47b42c3091b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4XPIADPHVG7MOA4DBHZH4IW6N3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mengyang Li, Zhong Zhang","submitted_at":"2025-04-10T15:32:00Z","abstract_excerpt":"Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, traditional DPO methods are limited by their reliance on single preference pairs. Recent work like Curriculum-DPO integrates multiple pairs using a one-dimensional difficulty curriculum based on pairwise distinguishability (PD), but overlooks the complexity of the input prompt itself. To address this, we propose 2D-Curri-DPO, a novel framework employing a two-dimensional curriculum t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07856","kind":"arxiv","version":3},"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/2504.07856/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":"2026-07-05T11:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I98nEcfv9I5kTkdAgsOrnoVseMeWtoO3gJvsx/T1S79lfrHk3LYFsK5UgNzPrkG4M1euaS56DD2296WEhj5QCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:48:08.519973Z"},"content_sha256":"19aaa0ef550a383b9877e62b9bda1a8c2777091734be6b8f5296dc617b4e5e81","schema_version":"1.0","event_id":"sha256:19aaa0ef550a383b9877e62b9bda1a8c2777091734be6b8f5296dc617b4e5e81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4XPIADPHVG7MOA4DBHZH4IW6N3/bundle.json","state_url":"https://pith.science/pith/4XPIADPHVG7MOA4DBHZH4IW6N3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4XPIADPHVG7MOA4DBHZH4IW6N3/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":"2026-08-08T20:48:08Z","links":{"resolver":"https://pith.science/pith/4XPIADPHVG7MOA4DBHZH4IW6N3","bundle":"https://pith.science/pith/4XPIADPHVG7MOA4DBHZH4IW6N3/bundle.json","state":"https://pith.science/pith/4XPIADPHVG7MOA4DBHZH4IW6N3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4XPIADPHVG7MOA4DBHZH4IW6N3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4XPIADPHVG7MOA4DBHZH4IW6N3","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":"4270507560a4329935ab2ff6740e280b19d9d6b19ea57750dbe91eed149d1c53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T15:32:00Z","title_canon_sha256":"12c04a50f9d9ad7bddd82583df969420a0f0c4c69d88274c17d2e9ce1ef01881"},"schema_version":"1.0","source":{"id":"2504.07856","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07856","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07856v3","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07856","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"4XPIADPHVG7M","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_16","alias_value":"4XPIADPHVG7MOA4D","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_8","alias_value":"4XPIADPH","created_at":"2026-07-05T11:44:47Z"}],"graph_snapshots":[{"event_id":"sha256:19aaa0ef550a383b9877e62b9bda1a8c2777091734be6b8f5296dc617b4e5e81","target":"graph","created_at":"2026-07-05T11:44:47Z","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/2504.07856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, traditional DPO methods are limited by their reliance on single preference pairs. Recent work like Curriculum-DPO integrates multiple pairs using a one-dimensional difficulty curriculum based on pairwise distinguishability (PD), but overlooks the complexity of the input prompt itself. To address this, we propose 2D-Curri-DPO, a novel framework employing a two-dimensional curriculum t","authors_text":"Mengyang Li, Zhong Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T15:32:00Z","title":"2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07856","kind":"arxiv","version":3},"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:a507fa71bf363e99d7a571d08e6c68c06d47fa8633ea45a8484ec47b42c3091b","target":"record","created_at":"2026-07-05T11:44:47Z","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":"4270507560a4329935ab2ff6740e280b19d9d6b19ea57750dbe91eed149d1c53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T15:32:00Z","title_canon_sha256":"12c04a50f9d9ad7bddd82583df969420a0f0c4c69d88274c17d2e9ce1ef01881"},"schema_version":"1.0","source":{"id":"2504.07856","kind":"arxiv","version":3}},"canonical_sha256":"e5de800de7a9bec7038309f27e22de6efe3994f11501fa34844f70218996e485","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5de800de7a9bec7038309f27e22de6efe3994f11501fa34844f70218996e485","first_computed_at":"2026-07-05T11:44:47.659395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:47.659395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eJ6+y/wsio0RrUtUlg78HOBCpmyo1Kk2WxQCV0uP/NJjD0TKdtK16k7k6FdyAQbySqT7QetPBeHESoLrN40gDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:47.659872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07856","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a507fa71bf363e99d7a571d08e6c68c06d47fa8633ea45a8484ec47b42c3091b","sha256:19aaa0ef550a383b9877e62b9bda1a8c2777091734be6b8f5296dc617b4e5e81"],"state_sha256":"b99e3f4a7069640cf200429fc981cdad1cc4f7fc00b60ef838c5287ab015dec2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"waB2yyVRgOU3tmxGtf4WHqcqhsBTxv/M517adzh4d18++6OTQXKSIAY5+jKHNP00tnna/n3W0UDhXcrVwEYwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:48:08.524375Z","bundle_sha256":"2487dfb8f3c0da97e11e399f8006b1feba6c489a9855af0c155c014c0d38cad1"}}