{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NRLL5TVLAKM7ZMHLZW77CTII6Q","short_pith_number":"pith:NRLL5TVL","canonical_record":{"source":{"id":"2506.21545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:59:07Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"title_canon_sha256":"8f5047f37dd27f8ecf22b2c44a7c1a9a13ebb6117b2cb45a38db8be8b6b02e2f","abstract_canon_sha256":"cc2c58c6ba57379f66030f535db1e4945517c557a1a44d042e4dde54a28aa3ac"},"schema_version":"1.0"},"canonical_sha256":"6c56beceab0299fcb0ebcdbff14d08f40f558dfe072bab50efe8b2678dc5fc36","source":{"kind":"arxiv","id":"2506.21545","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21545","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21545v1","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21545","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"NRLL5TVLAKM7","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"NRLL5TVLAKM7ZMHL","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"NRLL5TVL","created_at":"2026-07-05T11:27:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NRLL5TVLAKM7ZMHLZW77CTII6Q","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:59:07Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"title_canon_sha256":"8f5047f37dd27f8ecf22b2c44a7c1a9a13ebb6117b2cb45a38db8be8b6b02e2f","abstract_canon_sha256":"cc2c58c6ba57379f66030f535db1e4945517c557a1a44d042e4dde54a28aa3ac"},"schema_version":"1.0"},"canonical_sha256":"6c56beceab0299fcb0ebcdbff14d08f40f558dfe072bab50efe8b2678dc5fc36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:56.181477Z","signature_b64":"yztH90mS5POUVHDEuQI672QmFlLPcho7ABGvtp6sdu1H4oFOqcpnQOyDjjChKhtWhVMi4+joUZ+Vf2J3oydrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c56beceab0299fcb0ebcdbff14d08f40f558dfe072bab50efe8b2678dc5fc36","last_reissued_at":"2026-07-05T11:27:56.180919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:56.180919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21545","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":"2026-07-05T11:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Lgk/xXGOus+agsot460YZeb6Lv1P6gOefmzlASEkW6VKch2diVyUjndsg17cJPBCHrFjNNWhCY0qou7nunMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:47:25.691057Z"},"content_sha256":"a3a8716a943e802a4cb2f8389c967b16c3f5fdee2b3f09d7661ae0b1067eed05","schema_version":"1.0","event_id":"sha256:a3a8716a943e802a4cb2f8389c967b16c3f5fdee2b3f09d7661ae0b1067eed05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NRLL5TVLAKM7ZMHLZW77CTII6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Efficacy for Language Model Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.CL","authors_text":"Chong Li, Li Dong, Scarlett Li, Shijie Cao, Wenhui Lu, Wenshan Wu, Xin Zhang, Yalun Dai, Yangyu Huang","submitted_at":"2025-06-26T17:59:07Z","abstract_excerpt":"Data is fundamental to the training of language models (LM). Recent research has been dedicated to data efficiency, which aims to maximize performance by selecting a minimal or optimal subset of training data. Techniques such as data filtering, sampling, and selection play a crucial role in this area. To complement it, we define Data Efficacy, which focuses on maximizing performance by optimizing the organization of training data and remains relatively underexplored. This work introduces a general paradigm, DELT, for considering data efficacy in LM training, which highlights the significance o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21545","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/2506.21545/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":"2026-07-05T11:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ql086zaS3HlLFA/3xC6Jty1JYvYp9XEfVH4UUWBxJRciocYhVVIQyc+ZDgh2XsK5ySaa1wCwkgn+DOfxaqtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:47:25.692035Z"},"content_sha256":"abb079072908d3bf0c99b2185ce581246dfabe16e4f4d882c164d0b61e66e30e","schema_version":"1.0","event_id":"sha256:abb079072908d3bf0c99b2185ce581246dfabe16e4f4d882c164d0b61e66e30e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRLL5TVLAKM7ZMHLZW77CTII6Q/bundle.json","state_url":"https://pith.science/pith/NRLL5TVLAKM7ZMHLZW77CTII6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRLL5TVLAKM7ZMHLZW77CTII6Q/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":"2026-08-08T21:47:25Z","links":{"resolver":"https://pith.science/pith/NRLL5TVLAKM7ZMHLZW77CTII6Q","bundle":"https://pith.science/pith/NRLL5TVLAKM7ZMHLZW77CTII6Q/bundle.json","state":"https://pith.science/pith/NRLL5TVLAKM7ZMHLZW77CTII6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRLL5TVLAKM7ZMHLZW77CTII6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NRLL5TVLAKM7ZMHLZW77CTII6Q","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":"cc2c58c6ba57379f66030f535db1e4945517c557a1a44d042e4dde54a28aa3ac","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:59:07Z","title_canon_sha256":"8f5047f37dd27f8ecf22b2c44a7c1a9a13ebb6117b2cb45a38db8be8b6b02e2f"},"schema_version":"1.0","source":{"id":"2506.21545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21545","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21545v1","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21545","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"NRLL5TVLAKM7","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"NRLL5TVLAKM7ZMHL","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"NRLL5TVL","created_at":"2026-07-05T11:27:56Z"}],"graph_snapshots":[{"event_id":"sha256:abb079072908d3bf0c99b2185ce581246dfabe16e4f4d882c164d0b61e66e30e","target":"graph","created_at":"2026-07-05T11:27:56Z","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/2506.21545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data is fundamental to the training of language models (LM). Recent research has been dedicated to data efficiency, which aims to maximize performance by selecting a minimal or optimal subset of training data. Techniques such as data filtering, sampling, and selection play a crucial role in this area. To complement it, we define Data Efficacy, which focuses on maximizing performance by optimizing the organization of training data and remains relatively underexplored. This work introduces a general paradigm, DELT, for considering data efficacy in LM training, which highlights the significance o","authors_text":"Chong Li, Li Dong, Scarlett Li, Shijie Cao, Wenhui Lu, Wenshan Wu, Xin Zhang, Yalun Dai, Yangyu Huang","cross_cats":["cs.AI","cs.LG","cs.PF"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:59:07Z","title":"Data Efficacy for Language Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21545","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:a3a8716a943e802a4cb2f8389c967b16c3f5fdee2b3f09d7661ae0b1067eed05","target":"record","created_at":"2026-07-05T11:27:56Z","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":"cc2c58c6ba57379f66030f535db1e4945517c557a1a44d042e4dde54a28aa3ac","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:59:07Z","title_canon_sha256":"8f5047f37dd27f8ecf22b2c44a7c1a9a13ebb6117b2cb45a38db8be8b6b02e2f"},"schema_version":"1.0","source":{"id":"2506.21545","kind":"arxiv","version":1}},"canonical_sha256":"6c56beceab0299fcb0ebcdbff14d08f40f558dfe072bab50efe8b2678dc5fc36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c56beceab0299fcb0ebcdbff14d08f40f558dfe072bab50efe8b2678dc5fc36","first_computed_at":"2026-07-05T11:27:56.180919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:56.180919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yztH90mS5POUVHDEuQI672QmFlLPcho7ABGvtp6sdu1H4oFOqcpnQOyDjjChKhtWhVMi4+joUZ+Vf2J3oydrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:56.181477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3a8716a943e802a4cb2f8389c967b16c3f5fdee2b3f09d7661ae0b1067eed05","sha256:abb079072908d3bf0c99b2185ce581246dfabe16e4f4d882c164d0b61e66e30e"],"state_sha256":"cc7730ed15ddc42a1b30b180bb78b803cf1d7384ab29caab6173dcd911978771"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TT1NI9u079Tj3xNlk9kNt15D1GgvOWcp1o2DZdo3defj347szFtwkETeB1Cuyf2jugIrdFVgHD9mT3PQgo3nAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:47:25.698151Z","bundle_sha256":"56f661223c7ff614e104c602dbc10c6ec3ae4024aad8a57b41b4d07ff0ef2013"}}