{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E4H3J5NLSYX5U2ZZTLVPV7SI4R","short_pith_number":"pith:E4H3J5NL","canonical_record":{"source":{"id":"2407.01492","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:31:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22851f3e80ab57316e175c3f656d79fc5348aaca7fe2d252940f3cf1c395b61c","abstract_canon_sha256":"277480a45afe1ef27ff0f53a0ebc0565d28e403dd59af5e6bac75dc4fe95e9b8"},"schema_version":"1.0"},"canonical_sha256":"270fb4f5ab962fda6b399aeafafe48e47172522be96977b74c67a35f8522ddf3","source":{"kind":"arxiv","id":"2407.01492","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01492","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01492v2","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01492","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"E4H3J5NLSYX5","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"E4H3J5NLSYX5U2ZZ","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"E4H3J5NL","created_at":"2026-07-05T10:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E4H3J5NLSYX5U2ZZTLVPV7SI4R","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01492","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:31:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22851f3e80ab57316e175c3f656d79fc5348aaca7fe2d252940f3cf1c395b61c","abstract_canon_sha256":"277480a45afe1ef27ff0f53a0ebc0565d28e403dd59af5e6bac75dc4fe95e9b8"},"schema_version":"1.0"},"canonical_sha256":"270fb4f5ab962fda6b399aeafafe48e47172522be96977b74c67a35f8522ddf3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:14.321463Z","signature_b64":"yeeup4zMHHdx5zk2dJVJZDxOs9yYQsPv+C5VJ8rjd3QV70ODPTas3CSc0GiwRRdVpHipYumzBGsQmns0lWojBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"270fb4f5ab962fda6b399aeafafe48e47172522be96977b74c67a35f8522ddf3","last_reissued_at":"2026-07-05T10:04:14.320998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:14.320998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01492","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":"2026-07-05T10:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VxPNJ4IOlLgAhpVmnFMV+Mn7Jajc0Fq4MkUn5IMuHPUcK5X/l3msu+Zlk7b2OSBW3WImhWqJl/dPFB9/bWCeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:50:38.494517Z"},"content_sha256":"afeccfaf6d1c7abca5cf5d406bfed83b0f319df7dd6478365f97514d8b8fa6c5","schema_version":"1.0","event_id":"sha256:afeccfaf6d1c7abca5cf5d406bfed83b0f319df7dd6478365f97514d8b8fa6c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E4H3J5NLSYX5U2ZZTLVPV7SI4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RegMix: Data Mixture as Regression for Language Model Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangtao Zeng, Jing Jiang, Longxu Dou, Min Lin, Niklas Muennighoff, Qian Liu, Tianyu Pang, Xiaosen Zheng","submitted_at":"2024-07-01T17:31:03Z","abstract_excerpt":"The data mixture for large language model pre-training significantly impacts performance, yet how to determine an effective mixture remains unclear. We propose RegMix to automatically identify a high-performing data mixture by formulating it as a regression task. RegMix trains many small models on diverse data mixtures, uses regression to predict performance of unseen mixtures, and applies the best predicted mixture to train a large-scale model with orders of magnitude more compute. To empirically validate RegMix, we train 512 models with 1M parameters for 1B tokens to fit the regression model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01492","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/2407.01492/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":"2026-07-05T10:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jtmIy+0hBecsZOPLzED4pxaDnTiHxP4qzyOtCgDzgOzblmZ7GId7E0UO98cRRuz8Va/uixNmbmvwDvUYRSZ6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:50:38.495021Z"},"content_sha256":"1fc6e5876566ac1dccf59876d1cc39570c280ceacd6ed70e005d2d6bf3ceda50","schema_version":"1.0","event_id":"sha256:1fc6e5876566ac1dccf59876d1cc39570c280ceacd6ed70e005d2d6bf3ceda50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4H3J5NLSYX5U2ZZTLVPV7SI4R/bundle.json","state_url":"https://pith.science/pith/E4H3J5NLSYX5U2ZZTLVPV7SI4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4H3J5NLSYX5U2ZZTLVPV7SI4R/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":"2026-08-11T00:50:38Z","links":{"resolver":"https://pith.science/pith/E4H3J5NLSYX5U2ZZTLVPV7SI4R","bundle":"https://pith.science/pith/E4H3J5NLSYX5U2ZZTLVPV7SI4R/bundle.json","state":"https://pith.science/pith/E4H3J5NLSYX5U2ZZTLVPV7SI4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4H3J5NLSYX5U2ZZTLVPV7SI4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E4H3J5NLSYX5U2ZZTLVPV7SI4R","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":"277480a45afe1ef27ff0f53a0ebc0565d28e403dd59af5e6bac75dc4fe95e9b8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:31:03Z","title_canon_sha256":"22851f3e80ab57316e175c3f656d79fc5348aaca7fe2d252940f3cf1c395b61c"},"schema_version":"1.0","source":{"id":"2407.01492","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01492","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01492v2","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01492","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"E4H3J5NLSYX5","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"E4H3J5NLSYX5U2ZZ","created_at":"2026-07-05T10:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"E4H3J5NL","created_at":"2026-07-05T10:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:1fc6e5876566ac1dccf59876d1cc39570c280ceacd6ed70e005d2d6bf3ceda50","target":"graph","created_at":"2026-07-05T10:04:14Z","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/2407.01492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The data mixture for large language model pre-training significantly impacts performance, yet how to determine an effective mixture remains unclear. We propose RegMix to automatically identify a high-performing data mixture by formulating it as a regression task. RegMix trains many small models on diverse data mixtures, uses regression to predict performance of unseen mixtures, and applies the best predicted mixture to train a large-scale model with orders of magnitude more compute. To empirically validate RegMix, we train 512 models with 1M parameters for 1B tokens to fit the regression model","authors_text":"Guangtao Zeng, Jing Jiang, Longxu Dou, Min Lin, Niklas Muennighoff, Qian Liu, Tianyu Pang, Xiaosen Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:31:03Z","title":"RegMix: Data Mixture as Regression for Language Model Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01492","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:afeccfaf6d1c7abca5cf5d406bfed83b0f319df7dd6478365f97514d8b8fa6c5","target":"record","created_at":"2026-07-05T10:04:14Z","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":"277480a45afe1ef27ff0f53a0ebc0565d28e403dd59af5e6bac75dc4fe95e9b8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T17:31:03Z","title_canon_sha256":"22851f3e80ab57316e175c3f656d79fc5348aaca7fe2d252940f3cf1c395b61c"},"schema_version":"1.0","source":{"id":"2407.01492","kind":"arxiv","version":2}},"canonical_sha256":"270fb4f5ab962fda6b399aeafafe48e47172522be96977b74c67a35f8522ddf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"270fb4f5ab962fda6b399aeafafe48e47172522be96977b74c67a35f8522ddf3","first_computed_at":"2026-07-05T10:04:14.320998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:14.320998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yeeup4zMHHdx5zk2dJVJZDxOs9yYQsPv+C5VJ8rjd3QV70ODPTas3CSc0GiwRRdVpHipYumzBGsQmns0lWojBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:14.321463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01492","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afeccfaf6d1c7abca5cf5d406bfed83b0f319df7dd6478365f97514d8b8fa6c5","sha256:1fc6e5876566ac1dccf59876d1cc39570c280ceacd6ed70e005d2d6bf3ceda50"],"state_sha256":"25946c6094870f02f888ee49be15205cefebe7ad0db10b0c13f2350193287987"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cwb8+GBSJ0eRRk3bXwgE2zezmAyos96MIL7IvZmMlCqQ8z/nuMAdaNdPv/DDeY7c/LKzivpkwKcjNO/qrGCDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:50:38.498756Z","bundle_sha256":"98b2f0295adea60fd9fcbab978720f24eadb6a5f5028b149498288599e90c008"}}