{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TUPS347FM77TYXD2XJI3DWF3BS","short_pith_number":"pith:TUPS347F","canonical_record":{"source":{"id":"2504.13227","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T13:09:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9fb377428628c218e013c91e278d8f3968212bcdb378eaab8e0d9783c31b540b","abstract_canon_sha256":"e73bab70f2e36d041016847ddf970e608bf191d8e217a09b3b716bbf6e557fc6"},"schema_version":"1.0"},"canonical_sha256":"9d1f2df3e567ff3c5c7aba51b1d8bb0ca649961dc22658cf27e35b90fd0b8891","source":{"kind":"arxiv","id":"2504.13227","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13227","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13227v2","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13227","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"TUPS347FM77T","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"pith_short_16","alias_value":"TUPS347FM77TYXD2","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"pith_short_8","alias_value":"TUPS347F","created_at":"2026-07-05T11:57:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TUPS347FM77TYXD2XJI3DWF3BS","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13227","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T13:09:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9fb377428628c218e013c91e278d8f3968212bcdb378eaab8e0d9783c31b540b","abstract_canon_sha256":"e73bab70f2e36d041016847ddf970e608bf191d8e217a09b3b716bbf6e557fc6"},"schema_version":"1.0"},"canonical_sha256":"9d1f2df3e567ff3c5c7aba51b1d8bb0ca649961dc22658cf27e35b90fd0b8891","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:36.077152Z","signature_b64":"p0ksfb1CMeeBQeDQur3lkq99LV7kb1Y5iBhgAYNRpCWHCFXpKSUttLBrnFbNYHd9EMLR7irTeyeoSitRYSK2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d1f2df3e567ff3c5c7aba51b1d8bb0ca649961dc22658cf27e35b90fd0b8891","last_reissued_at":"2026-07-05T11:57:36.076658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:36.076658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13227","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":"2026-07-05T11:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2nJJhxfOQkQcTDehnJTaZJKZD376r+4ZSRQIhP0wi03GS3fZtXpNHLtoskX6+72iXroThODpMYTLeWKSCUZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T05:03:30.732357Z"},"content_sha256":"973e32bcfc85c894fd388dba79e0e36f6382348a02c4cc85808b1500049bfa84","schema_version":"1.0","event_id":"sha256:973e32bcfc85c894fd388dba79e0e36f6382348a02c4cc85808b1500049bfa84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TUPS347FM77TYXD2XJI3DWF3BS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DIDS: Domain Impact-aware Data Sampling for Large Language Model Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Chen, Jiajie Xu, Jia Zhu, Jingzhi Fang, Jipeng Zhang, Ruiyuan Zhang, Sirui Han, Weijie Shi, Xiaofang Zhou, Yaguang Wu, Yao Zhao","submitted_at":"2025-04-17T13:09:38Z","abstract_excerpt":"Large language models (LLMs) are commonly trained on multi-domain datasets, where domain sampling strategies significantly impact model performance due to varying domain importance across downstream tasks. Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact. In this paper, we present Domain Impact-aware Data Sampling (DIDS). To ensure intra-domain consistency, a gradient clustering algorithm is proposed to group training data based on their learning effects, where a proxy language model an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13227","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/2504.13227/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":"2026-07-05T11:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9cvDUDDirRh+ZVRBq32itI/LyotdeJTiXDqCy3uMs987XeAz9HiR7vF2fZx+XCcoDj6H1bO6H1Zbnz928x8IDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T05:03:30.732685Z"},"content_sha256":"1226846c299c2d56c8abd769afa81b756ccd6378a6a4c16eb9e8acb1b60f9ab4","schema_version":"1.0","event_id":"sha256:1226846c299c2d56c8abd769afa81b756ccd6378a6a4c16eb9e8acb1b60f9ab4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUPS347FM77TYXD2XJI3DWF3BS/bundle.json","state_url":"https://pith.science/pith/TUPS347FM77TYXD2XJI3DWF3BS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUPS347FM77TYXD2XJI3DWF3BS/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":"2026-08-20T05:03:30Z","links":{"resolver":"https://pith.science/pith/TUPS347FM77TYXD2XJI3DWF3BS","bundle":"https://pith.science/pith/TUPS347FM77TYXD2XJI3DWF3BS/bundle.json","state":"https://pith.science/pith/TUPS347FM77TYXD2XJI3DWF3BS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUPS347FM77TYXD2XJI3DWF3BS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TUPS347FM77TYXD2XJI3DWF3BS","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":"e73bab70f2e36d041016847ddf970e608bf191d8e217a09b3b716bbf6e557fc6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T13:09:38Z","title_canon_sha256":"9fb377428628c218e013c91e278d8f3968212bcdb378eaab8e0d9783c31b540b"},"schema_version":"1.0","source":{"id":"2504.13227","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13227","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13227v2","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13227","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"TUPS347FM77T","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"pith_short_16","alias_value":"TUPS347FM77TYXD2","created_at":"2026-07-05T11:57:36Z"},{"alias_kind":"pith_short_8","alias_value":"TUPS347F","created_at":"2026-07-05T11:57:36Z"}],"graph_snapshots":[{"event_id":"sha256:1226846c299c2d56c8abd769afa81b756ccd6378a6a4c16eb9e8acb1b60f9ab4","target":"graph","created_at":"2026-07-05T11:57:36Z","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/2504.13227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are commonly trained on multi-domain datasets, where domain sampling strategies significantly impact model performance due to varying domain importance across downstream tasks. Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact. In this paper, we present Domain Impact-aware Data Sampling (DIDS). To ensure intra-domain consistency, a gradient clustering algorithm is proposed to group training data based on their learning effects, where a proxy language model an","authors_text":"Hao Chen, Jiajie Xu, Jia Zhu, Jingzhi Fang, Jipeng Zhang, Ruiyuan Zhang, Sirui Han, Weijie Shi, Xiaofang Zhou, Yaguang Wu, Yao Zhao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T13:09:38Z","title":"DIDS: Domain Impact-aware Data Sampling for Large Language Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13227","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":"sha256:973e32bcfc85c894fd388dba79e0e36f6382348a02c4cc85808b1500049bfa84","target":"record","created_at":"2026-07-05T11:57:36Z","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":"e73bab70f2e36d041016847ddf970e608bf191d8e217a09b3b716bbf6e557fc6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T13:09:38Z","title_canon_sha256":"9fb377428628c218e013c91e278d8f3968212bcdb378eaab8e0d9783c31b540b"},"schema_version":"1.0","source":{"id":"2504.13227","kind":"arxiv","version":2}},"canonical_sha256":"9d1f2df3e567ff3c5c7aba51b1d8bb0ca649961dc22658cf27e35b90fd0b8891","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d1f2df3e567ff3c5c7aba51b1d8bb0ca649961dc22658cf27e35b90fd0b8891","first_computed_at":"2026-07-05T11:57:36.076658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:36.076658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p0ksfb1CMeeBQeDQur3lkq99LV7kb1Y5iBhgAYNRpCWHCFXpKSUttLBrnFbNYHd9EMLR7irTeyeoSitRYSK2Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:36.077152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13227","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:973e32bcfc85c894fd388dba79e0e36f6382348a02c4cc85808b1500049bfa84","sha256:1226846c299c2d56c8abd769afa81b756ccd6378a6a4c16eb9e8acb1b60f9ab4"],"state_sha256":"7b6032ef284ce5c761c89484364118dc827e5dd61ae15e08af1ef9831ef19641"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3tWJJOjSaJKyqktz3IKbwoeg49chd7AhR6K4McL3VNxKTUC6e0UKskLxeIN/J/rjZgZS15eDyYxqzXM10MOoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T05:03:30.736259Z","bundle_sha256":"7867dfaf3481e1638d065d780f53d1ff89556ed4c55b69de4d8f926af23afefa"}}