{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QMQKSZ6JIBN7QA7UKCI2RG5SPQ","short_pith_number":"pith:QMQKSZ6J","canonical_record":{"source":{"id":"2507.03004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T06:19:40Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"0b2c55fc88b15da3f1d8e4ddb89a921cf277d28d5afa7dae498aa594a60debc4","abstract_canon_sha256":"6910f2de3a4f9219712328d4942f123ae59cd05d46c6b4926da4437941482685"},"schema_version":"1.0"},"canonical_sha256":"8320a967c9405bf803f45091a89bb27c373a96d5df125bd5b1e1d41f1903f14b","source":{"kind":"arxiv","id":"2507.03004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03004","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03004v1","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03004","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"QMQKSZ6JIBN7","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"QMQKSZ6JIBN7QA7U","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"QMQKSZ6J","created_at":"2026-07-05T11:31:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QMQKSZ6JIBN7QA7UKCI2RG5SPQ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T06:19:40Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"0b2c55fc88b15da3f1d8e4ddb89a921cf277d28d5afa7dae498aa594a60debc4","abstract_canon_sha256":"6910f2de3a4f9219712328d4942f123ae59cd05d46c6b4926da4437941482685"},"schema_version":"1.0"},"canonical_sha256":"8320a967c9405bf803f45091a89bb27c373a96d5df125bd5b1e1d41f1903f14b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:50.602010Z","signature_b64":"mt+iUsaEMhIRApCAuRIjCRrYjpvk6bG0Kd3pk9cX63f3JzLpG+7/2MjcLx9jcjjnJkEsCeKyYvthh1/9v4HACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8320a967c9405bf803f45091a89bb27c373a96d5df125bd5b1e1d41f1903f14b","last_reissued_at":"2026-07-05T11:31:50.601509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:50.601509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03004","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":"2026-07-05T11:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9QI1yZE8+XFJMnnfFKEgtN9w0iQfIge1m1s+nqI93r1bf3yQJmjbTjk8pHBgKaEk+vCJ45VpbU5iJiDX/ptDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:58:21.453102Z"},"content_sha256":"3477476a84ec66adbeb7e306415d90940c5a40360f007bbc436a260ccc7c5882","schema_version":"1.0","event_id":"sha256:3477476a84ec66adbeb7e306415d90940c5a40360f007bbc436a260ccc7c5882"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QMQKSZ6JIBN7QA7UKCI2RG5SPQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.CL","authors_text":"Bofan Chen, Hongxiang Fan, Nicholas D. Lane, Shell Xu Hu, Wangchunshu Zhou, Wanru Zhao","submitted_at":"2025-07-02T06:19:40Z","abstract_excerpt":"Recent research has highlighted the importance of data quality in scaling large language models (LLMs). However, automated data quality control faces unique challenges in collaborative settings where sharing is not allowed directly between data silos. To tackle this issue, this paper proposes a novel data quality control technique based on the notion of data influence on the training dynamics of LLMs, that high quality data are more likely to have similar training dynamics to the anchor dataset. We then leverage the influence of the training dynamics to select high-quality data from different "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03004","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/2507.03004/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":"2026-07-05T11:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ixZ0q/FjJp0vvcvxkfIE56iJ0+xLvqTdx1xKA6JAFQ/B1XwXjuEEtsKkRu8dTEWTgH6V3+We2tKMZAGfRA1CBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:58:21.453616Z"},"content_sha256":"0ff33a0b92f7dbe43628718a967333387d052f405d3f99e7879108ea97df4a36","schema_version":"1.0","event_id":"sha256:0ff33a0b92f7dbe43628718a967333387d052f405d3f99e7879108ea97df4a36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMQKSZ6JIBN7QA7UKCI2RG5SPQ/bundle.json","state_url":"https://pith.science/pith/QMQKSZ6JIBN7QA7UKCI2RG5SPQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMQKSZ6JIBN7QA7UKCI2RG5SPQ/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":"2026-08-07T12:58:21Z","links":{"resolver":"https://pith.science/pith/QMQKSZ6JIBN7QA7UKCI2RG5SPQ","bundle":"https://pith.science/pith/QMQKSZ6JIBN7QA7UKCI2RG5SPQ/bundle.json","state":"https://pith.science/pith/QMQKSZ6JIBN7QA7UKCI2RG5SPQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMQKSZ6JIBN7QA7UKCI2RG5SPQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QMQKSZ6JIBN7QA7UKCI2RG5SPQ","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":"6910f2de3a4f9219712328d4942f123ae59cd05d46c6b4926da4437941482685","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T06:19:40Z","title_canon_sha256":"0b2c55fc88b15da3f1d8e4ddb89a921cf277d28d5afa7dae498aa594a60debc4"},"schema_version":"1.0","source":{"id":"2507.03004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03004","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03004v1","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03004","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"QMQKSZ6JIBN7","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"QMQKSZ6JIBN7QA7U","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"QMQKSZ6J","created_at":"2026-07-05T11:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:0ff33a0b92f7dbe43628718a967333387d052f405d3f99e7879108ea97df4a36","target":"graph","created_at":"2026-07-05T11:31:50Z","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/2507.03004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research has highlighted the importance of data quality in scaling large language models (LLMs). However, automated data quality control faces unique challenges in collaborative settings where sharing is not allowed directly between data silos. To tackle this issue, this paper proposes a novel data quality control technique based on the notion of data influence on the training dynamics of LLMs, that high quality data are more likely to have similar training dynamics to the anchor dataset. We then leverage the influence of the training dynamics to select high-quality data from different ","authors_text":"Bofan Chen, Hongxiang Fan, Nicholas D. Lane, Shell Xu Hu, Wangchunshu Zhou, Wanru Zhao","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T06:19:40Z","title":"CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03004","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":"sha256:3477476a84ec66adbeb7e306415d90940c5a40360f007bbc436a260ccc7c5882","target":"record","created_at":"2026-07-05T11:31:50Z","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":"6910f2de3a4f9219712328d4942f123ae59cd05d46c6b4926da4437941482685","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T06:19:40Z","title_canon_sha256":"0b2c55fc88b15da3f1d8e4ddb89a921cf277d28d5afa7dae498aa594a60debc4"},"schema_version":"1.0","source":{"id":"2507.03004","kind":"arxiv","version":1}},"canonical_sha256":"8320a967c9405bf803f45091a89bb27c373a96d5df125bd5b1e1d41f1903f14b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8320a967c9405bf803f45091a89bb27c373a96d5df125bd5b1e1d41f1903f14b","first_computed_at":"2026-07-05T11:31:50.601509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:50.601509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mt+iUsaEMhIRApCAuRIjCRrYjpvk6bG0Kd3pk9cX63f3JzLpG+7/2MjcLx9jcjjnJkEsCeKyYvthh1/9v4HACA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:50.602010Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3477476a84ec66adbeb7e306415d90940c5a40360f007bbc436a260ccc7c5882","sha256:0ff33a0b92f7dbe43628718a967333387d052f405d3f99e7879108ea97df4a36"],"state_sha256":"73701f5fc39abcd7b7e8c0909e1894434bc5029f2ad418d9409a315767bb24bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fTMi/CVl+BBf1aZGlC75nc8bMbvVLUA+10L/kY74YvaiKwdgM20kT8EzZqHKY7XAMYEybluzQDJZ7yTNV6/YCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:58:21.458588Z","bundle_sha256":"a377f104c3ccc4cc9c639e945dd319e51174c80ebef72afa119a6299e688faab"}}