{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RU5L6FJXEDNOK6ICG4WW5NARJK","short_pith_number":"pith:RU5L6FJX","canonical_record":{"source":{"id":"2402.16827","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:54:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b892ec169ba7c60bd533d61a043de4e3e86ffb98550ae479c460b979aea13a9e","abstract_canon_sha256":"705943456afaee5bf9df7259df2e19f7b2f9718de10551c1aae976a99a125623"},"schema_version":"1.0"},"canonical_sha256":"8d3abf153720dae57902372d6eb4114a80176da24ca5483da11edbedb8c38c60","source":{"kind":"arxiv","id":"2402.16827","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16827","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16827v3","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16827","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_12","alias_value":"RU5L6FJXEDNO","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_16","alias_value":"RU5L6FJXEDNOK6IC","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_8","alias_value":"RU5L6FJX","created_at":"2026-07-05T08:51:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RU5L6FJXEDNOK6ICG4WW5NARJK","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16827","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:54:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b892ec169ba7c60bd533d61a043de4e3e86ffb98550ae479c460b979aea13a9e","abstract_canon_sha256":"705943456afaee5bf9df7259df2e19f7b2f9718de10551c1aae976a99a125623"},"schema_version":"1.0"},"canonical_sha256":"8d3abf153720dae57902372d6eb4114a80176da24ca5483da11edbedb8c38c60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:37.149918Z","signature_b64":"d8NcO11buma0cCvQsRBFdGmO4As6Ihxi+MWCNdO2OkAF8Advg2jDR/DYRDY3CwUuCKETDjZ+oQV4DVIL1ZXYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d3abf153720dae57902372d6eb4114a80176da24ca5483da11edbedb8c38c60","last_reissued_at":"2026-07-05T08:51:37.149439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:37.149439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16827","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":"2026-07-05T08:51:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9dMnP/B32as2PRBSRU6KSzBkU6MXq+LvUWyeizjU/iOSPAWRL1ueZXWbQS9Kl+0IaoAJU5872ruTU9d5ZidXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:50.096645Z"},"content_sha256":"151e3d566e92c59c739da0e851430ce5bd13a976d3600e7d7ba7c7d4ccbd97a7","schema_version":"1.0","event_id":"sha256:151e3d566e92c59c739da0e851430ce5bd13a976d3600e7d7ba7c7d4ccbd97a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RU5L6FJXEDNOK6ICG4WW5NARJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Data Selection for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alon Albalak, Bairu Hou, Colin Raffel, Haewon Jeong, Liangming Pan, Nathan Lambert, Niklas Muennighoff, Sang Michael Xie, Shayne Longpre, Shiyu Chang, Tatsunori Hashimoto, William Yang Wang, Xinyi Wang, Yanai Elazar","submitted_at":"2024-02-26T18:54:35Z","abstract_excerpt":"A major factor in the recent success of large language models is the use of enormous and ever-growing text datasets for unsupervised pre-training. However, naively training a model on all available data may not be optimal (or feasible), as the quality of available text data can vary. Filtering out data can also decrease the carbon footprint and financial costs of training models by reducing the amount of training required. Data selection methods aim to determine which candidate data points to include in the training dataset and how to appropriately sample from the selected data points. The pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16827","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/2402.16827/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":"2026-07-05T08:51:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ssziB6xMe3nr3k09OLYso40cwhIM/vnWcjIdC26HwLpVpqiUlrWmu/fFVpLj4n9dupOVXchjvmTxzx31wfkLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:50.097507Z"},"content_sha256":"acdc44cb351d0338d89c57b80a1e55f8583f2762dcd95e5c8fd8bf02bf2d5a73","schema_version":"1.0","event_id":"sha256:acdc44cb351d0338d89c57b80a1e55f8583f2762dcd95e5c8fd8bf02bf2d5a73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RU5L6FJXEDNOK6ICG4WW5NARJK/bundle.json","state_url":"https://pith.science/pith/RU5L6FJXEDNOK6ICG4WW5NARJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RU5L6FJXEDNOK6ICG4WW5NARJK/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":"2026-08-05T01:48:50Z","links":{"resolver":"https://pith.science/pith/RU5L6FJXEDNOK6ICG4WW5NARJK","bundle":"https://pith.science/pith/RU5L6FJXEDNOK6ICG4WW5NARJK/bundle.json","state":"https://pith.science/pith/RU5L6FJXEDNOK6ICG4WW5NARJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RU5L6FJXEDNOK6ICG4WW5NARJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RU5L6FJXEDNOK6ICG4WW5NARJK","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":"705943456afaee5bf9df7259df2e19f7b2f9718de10551c1aae976a99a125623","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:54:35Z","title_canon_sha256":"b892ec169ba7c60bd533d61a043de4e3e86ffb98550ae479c460b979aea13a9e"},"schema_version":"1.0","source":{"id":"2402.16827","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16827","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16827v3","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16827","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_12","alias_value":"RU5L6FJXEDNO","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_16","alias_value":"RU5L6FJXEDNOK6IC","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_8","alias_value":"RU5L6FJX","created_at":"2026-07-05T08:51:37Z"}],"graph_snapshots":[{"event_id":"sha256:acdc44cb351d0338d89c57b80a1e55f8583f2762dcd95e5c8fd8bf02bf2d5a73","target":"graph","created_at":"2026-07-05T08:51:37Z","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/2402.16827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A major factor in the recent success of large language models is the use of enormous and ever-growing text datasets for unsupervised pre-training. However, naively training a model on all available data may not be optimal (or feasible), as the quality of available text data can vary. Filtering out data can also decrease the carbon footprint and financial costs of training models by reducing the amount of training required. Data selection methods aim to determine which candidate data points to include in the training dataset and how to appropriately sample from the selected data points. The pro","authors_text":"Alon Albalak, Bairu Hou, Colin Raffel, Haewon Jeong, Liangming Pan, Nathan Lambert, Niklas Muennighoff, Sang Michael Xie, Shayne Longpre, Shiyu Chang, Tatsunori Hashimoto, William Yang Wang, Xinyi Wang, Yanai Elazar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:54:35Z","title":"A Survey on Data Selection for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16827","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":"sha256:151e3d566e92c59c739da0e851430ce5bd13a976d3600e7d7ba7c7d4ccbd97a7","target":"record","created_at":"2026-07-05T08:51:37Z","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":"705943456afaee5bf9df7259df2e19f7b2f9718de10551c1aae976a99a125623","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:54:35Z","title_canon_sha256":"b892ec169ba7c60bd533d61a043de4e3e86ffb98550ae479c460b979aea13a9e"},"schema_version":"1.0","source":{"id":"2402.16827","kind":"arxiv","version":3}},"canonical_sha256":"8d3abf153720dae57902372d6eb4114a80176da24ca5483da11edbedb8c38c60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d3abf153720dae57902372d6eb4114a80176da24ca5483da11edbedb8c38c60","first_computed_at":"2026-07-05T08:51:37.149439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:37.149439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d8NcO11buma0cCvQsRBFdGmO4As6Ihxi+MWCNdO2OkAF8Advg2jDR/DYRDY3CwUuCKETDjZ+oQV4DVIL1ZXYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:37.149918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16827","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:151e3d566e92c59c739da0e851430ce5bd13a976d3600e7d7ba7c7d4ccbd97a7","sha256:acdc44cb351d0338d89c57b80a1e55f8583f2762dcd95e5c8fd8bf02bf2d5a73"],"state_sha256":"c0026a36ed0dd5a1e26c4cfc3729e3e7a201740c638ede69c0730e79fe5ed312"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FV6iir+qbUqBv8yyHbG2pwhgQShJb/gjsyFfFbt/Q5EvrJkk/gbqVOSG9RVW3HXuZuDqredfF+53E7U04dbxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:48:50.101821Z","bundle_sha256":"7d5f2d8e2eaafb88df3402622507a4251626fa3a9b5a2740e1111f26546cd6ca"}}