{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JVODK4BI5R5OZPMOUMPZCNFP2Y","short_pith_number":"pith:JVODK4BI","canonical_record":{"source":{"id":"2412.20996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-30T15:01:48Z","cross_cats_sorted":[],"title_canon_sha256":"ac53ae0bdb48c509151cf60554d8b032df19d1c393ab5886d72e1ad72110b197","abstract_canon_sha256":"b97b3d96d556d1865ef64a6abdf0067bfff947578f7cb704e9b6b6d76c8c9743"},"schema_version":"1.0"},"canonical_sha256":"4d5c357028ec7aecbd8ea31f9134afd63410255cc3ec6398594bfbc633d48c56","source":{"kind":"arxiv","id":"2412.20996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20996","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20996v1","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20996","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"pith_short_12","alias_value":"JVODK4BI5R5O","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"pith_short_16","alias_value":"JVODK4BI5R5OZPMO","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"pith_short_8","alias_value":"JVODK4BI","created_at":"2026-07-05T09:55:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JVODK4BI5R5OZPMOUMPZCNFP2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2412.20996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-30T15:01:48Z","cross_cats_sorted":[],"title_canon_sha256":"ac53ae0bdb48c509151cf60554d8b032df19d1c393ab5886d72e1ad72110b197","abstract_canon_sha256":"b97b3d96d556d1865ef64a6abdf0067bfff947578f7cb704e9b6b6d76c8c9743"},"schema_version":"1.0"},"canonical_sha256":"4d5c357028ec7aecbd8ea31f9134afd63410255cc3ec6398594bfbc633d48c56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:25.863573Z","signature_b64":"ykrOD/sGDJkXeqW3lI1U7TNCsvNOc3bOqZsWV4WA1XcHYjfeagrgoVMDkd8Jzee3nof0iMVos6TmQMHNYNZEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d5c357028ec7aecbd8ea31f9134afd63410255cc3ec6398594bfbc633d48c56","last_reissued_at":"2026-07-05T09:55:25.863079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:25.863079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.20996","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":"2026-07-05T09:55:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LYBKMx2toDLmTkRYusJCWI7hHN5bnTLfscde3T1c/sdziFQMUAYFsuZ0Pb0NdAo1wRyAJDgzRgIrARKXtKhNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:26:45.646627Z"},"content_sha256":"fc7dd1fc9446fd7867128871274aa48f7be1b266f0f0b917c132cfc99a31d3af","schema_version":"1.0","event_id":"sha256:fc7dd1fc9446fd7867128871274aa48f7be1b266f0f0b917c132cfc99a31d3af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JVODK4BI5R5OZPMOUMPZCNFP2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Plug-and-Play Training Framework for Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingyuan Ma, Lei Sha, Rui Li, Zheng Li, Zhifang Sui","submitted_at":"2024-12-30T15:01:48Z","abstract_excerpt":"Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty levels of training samples during preference optimization, leading to mediocre performance in tasks with high accuracy requirements, particularly in mathematical reasoning. To address this limitation, we propose a novel training framework, which employs multiple sampling to analyze output distributions, assign different weights to samples, and incorporate these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20996","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/2412.20996/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":"2026-07-05T09:55:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+No8JBS3RtRhIl6wAgB3fZ93LpDN765+UlF3HeeWrjq43HSqwUvScxVdMlhVkM0IKFy3aWJjaamIHGDA6xnVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:26:45.647866Z"},"content_sha256":"7f7719723da722e0d1a4c86da0809f9f69955896f71c6c7967cb9323948778e5","schema_version":"1.0","event_id":"sha256:7f7719723da722e0d1a4c86da0809f9f69955896f71c6c7967cb9323948778e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JVODK4BI5R5OZPMOUMPZCNFP2Y/bundle.json","state_url":"https://pith.science/pith/JVODK4BI5R5OZPMOUMPZCNFP2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JVODK4BI5R5OZPMOUMPZCNFP2Y/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":"2026-08-08T20:26:45Z","links":{"resolver":"https://pith.science/pith/JVODK4BI5R5OZPMOUMPZCNFP2Y","bundle":"https://pith.science/pith/JVODK4BI5R5OZPMOUMPZCNFP2Y/bundle.json","state":"https://pith.science/pith/JVODK4BI5R5OZPMOUMPZCNFP2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JVODK4BI5R5OZPMOUMPZCNFP2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JVODK4BI5R5OZPMOUMPZCNFP2Y","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":"b97b3d96d556d1865ef64a6abdf0067bfff947578f7cb704e9b6b6d76c8c9743","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-30T15:01:48Z","title_canon_sha256":"ac53ae0bdb48c509151cf60554d8b032df19d1c393ab5886d72e1ad72110b197"},"schema_version":"1.0","source":{"id":"2412.20996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20996","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20996v1","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20996","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"pith_short_12","alias_value":"JVODK4BI5R5O","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"pith_short_16","alias_value":"JVODK4BI5R5OZPMO","created_at":"2026-07-05T09:55:25Z"},{"alias_kind":"pith_short_8","alias_value":"JVODK4BI","created_at":"2026-07-05T09:55:25Z"}],"graph_snapshots":[{"event_id":"sha256:7f7719723da722e0d1a4c86da0809f9f69955896f71c6c7967cb9323948778e5","target":"graph","created_at":"2026-07-05T09:55:25Z","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/2412.20996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty levels of training samples during preference optimization, leading to mediocre performance in tasks with high accuracy requirements, particularly in mathematical reasoning. To address this limitation, we propose a novel training framework, which employs multiple sampling to analyze output distributions, assign different weights to samples, and incorporate these ","authors_text":"Jingyuan Ma, Lei Sha, Rui Li, Zheng Li, Zhifang Sui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-30T15:01:48Z","title":"Plug-and-Play Training Framework for Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20996","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:fc7dd1fc9446fd7867128871274aa48f7be1b266f0f0b917c132cfc99a31d3af","target":"record","created_at":"2026-07-05T09:55:25Z","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":"b97b3d96d556d1865ef64a6abdf0067bfff947578f7cb704e9b6b6d76c8c9743","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-30T15:01:48Z","title_canon_sha256":"ac53ae0bdb48c509151cf60554d8b032df19d1c393ab5886d72e1ad72110b197"},"schema_version":"1.0","source":{"id":"2412.20996","kind":"arxiv","version":1}},"canonical_sha256":"4d5c357028ec7aecbd8ea31f9134afd63410255cc3ec6398594bfbc633d48c56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d5c357028ec7aecbd8ea31f9134afd63410255cc3ec6398594bfbc633d48c56","first_computed_at":"2026-07-05T09:55:25.863079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:25.863079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ykrOD/sGDJkXeqW3lI1U7TNCsvNOc3bOqZsWV4WA1XcHYjfeagrgoVMDkd8Jzee3nof0iMVos6TmQMHNYNZEAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:25.863573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc7dd1fc9446fd7867128871274aa48f7be1b266f0f0b917c132cfc99a31d3af","sha256:7f7719723da722e0d1a4c86da0809f9f69955896f71c6c7967cb9323948778e5"],"state_sha256":"da98dc21ac7099eee32e48b400acddae2f3bfb25ee8530db8080cb8ae56d10a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DkJO+dhfCNqHXXEAuMwOh7A94CX+vgm6Rjn3gkIyXn7S8+zLWv4pfCTQ1tFBFhsP1Zr6zzKINI6FzWInh8mIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:26:45.657490Z","bundle_sha256":"fa3dc85d9727ba61803bd893c1327a6de580a39ec76907d83dcaf94ba586608b"}}