{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SOCYVDPU56UXP6P426CO5C3F4Q","short_pith_number":"pith:SOCYVDPU","canonical_record":{"source":{"id":"2403.16952","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T17:14:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b2c2d9e03dda579ff004073863c9757d0f2d664dac275d8bb3fa5c5d089787ba","abstract_canon_sha256":"c110feaa3099cf061cfef7efb381756bbe5b7006de764b764a3017eadb88b8c9"},"schema_version":"1.0"},"canonical_sha256":"93858a8df4efa977f9fcd784ee8b65e405190a7b2254e284b79c269735f92586","source":{"kind":"arxiv","id":"2403.16952","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16952","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16952v2","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16952","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"pith_short_12","alias_value":"SOCYVDPU56UX","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"pith_short_16","alias_value":"SOCYVDPU56UXP6P4","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"pith_short_8","alias_value":"SOCYVDPU","created_at":"2026-07-05T10:35:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SOCYVDPU56UXP6P426CO5C3F4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16952","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T17:14:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b2c2d9e03dda579ff004073863c9757d0f2d664dac275d8bb3fa5c5d089787ba","abstract_canon_sha256":"c110feaa3099cf061cfef7efb381756bbe5b7006de764b764a3017eadb88b8c9"},"schema_version":"1.0"},"canonical_sha256":"93858a8df4efa977f9fcd784ee8b65e405190a7b2254e284b79c269735f92586","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:32.078776Z","signature_b64":"GBiO/wLjWZse+U5tyZeqi3ZlKDZ20PNfnLo/xstzmqZ5lW4CPGL8t7ZtI8KNXEIJiTFLPoiAdKaCMhZBautEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93858a8df4efa977f9fcd784ee8b65e405190a7b2254e284b79c269735f92586","last_reissued_at":"2026-07-05T10:35:32.077756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:32.077756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16952","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":"2026-07-05T10:35:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5X8rrdZbMIVQxdSv6SNSRh5SyrMHRVDbAAFcIsjtM1PNuH3yJriP0LFZ0rlQS9Fw4AH4mccIxvIDjWVAJdVUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:15:30.049695Z"},"content_sha256":"97fc49813b8b585ee255f86f6986264883f589341d136178fd6d34f5f597de03","schema_version":"1.0","event_id":"sha256:97fc49813b8b585ee255f86f6986264883f589341d136178fd6d34f5f597de03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SOCYVDPU56UXP6P426CO5C3F4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiasheng Ye, Jun Zhan, Peiju Liu, Tianxiang Sun, Xipeng Qiu, Yunhua Zhou","submitted_at":"2024-03-25T17:14:00Z","abstract_excerpt":"Pretraining data of large language models composes multiple domains (e.g., web texts, academic papers, codes), whose mixture proportions crucially impact the competence of outcome models. While existing endeavors rely on heuristics or qualitative strategies to tune the proportions, we discover the quantitative predictability of model performance regarding the mixture proportions in function forms, which we refer to as the data mixing laws. Fitting such functions on sample mixtures unveils model performance on unseen mixtures before actual runs, thus guiding the selection of an ideal data mixtu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16952","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/2403.16952/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":"2026-07-05T10:35:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hxMYoU+oupa1jWNYDPsV4hhIIq/UGUj96o+R8dt0SRFW54g26SyHJYQAv0gBz8IAMBjhQaTmEiqN+AwKMdd/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:15:30.050195Z"},"content_sha256":"4f27c31e278169af06716452a3ac7dce64b0ec64ced682ca900a7c16d5cc2860","schema_version":"1.0","event_id":"sha256:4f27c31e278169af06716452a3ac7dce64b0ec64ced682ca900a7c16d5cc2860"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SOCYVDPU56UXP6P426CO5C3F4Q/bundle.json","state_url":"https://pith.science/pith/SOCYVDPU56UXP6P426CO5C3F4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SOCYVDPU56UXP6P426CO5C3F4Q/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":"2026-08-05T23:15:30Z","links":{"resolver":"https://pith.science/pith/SOCYVDPU56UXP6P426CO5C3F4Q","bundle":"https://pith.science/pith/SOCYVDPU56UXP6P426CO5C3F4Q/bundle.json","state":"https://pith.science/pith/SOCYVDPU56UXP6P426CO5C3F4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SOCYVDPU56UXP6P426CO5C3F4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SOCYVDPU56UXP6P426CO5C3F4Q","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":"c110feaa3099cf061cfef7efb381756bbe5b7006de764b764a3017eadb88b8c9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T17:14:00Z","title_canon_sha256":"b2c2d9e03dda579ff004073863c9757d0f2d664dac275d8bb3fa5c5d089787ba"},"schema_version":"1.0","source":{"id":"2403.16952","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16952","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16952v2","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16952","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"pith_short_12","alias_value":"SOCYVDPU56UX","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"pith_short_16","alias_value":"SOCYVDPU56UXP6P4","created_at":"2026-07-05T10:35:32Z"},{"alias_kind":"pith_short_8","alias_value":"SOCYVDPU","created_at":"2026-07-05T10:35:32Z"}],"graph_snapshots":[{"event_id":"sha256:4f27c31e278169af06716452a3ac7dce64b0ec64ced682ca900a7c16d5cc2860","target":"graph","created_at":"2026-07-05T10:35:32Z","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/2403.16952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining data of large language models composes multiple domains (e.g., web texts, academic papers, codes), whose mixture proportions crucially impact the competence of outcome models. While existing endeavors rely on heuristics or qualitative strategies to tune the proportions, we discover the quantitative predictability of model performance regarding the mixture proportions in function forms, which we refer to as the data mixing laws. Fitting such functions on sample mixtures unveils model performance on unseen mixtures before actual runs, thus guiding the selection of an ideal data mixtu","authors_text":"Jiasheng Ye, Jun Zhan, Peiju Liu, Tianxiang Sun, Xipeng Qiu, Yunhua Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T17:14:00Z","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16952","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":"sha256:97fc49813b8b585ee255f86f6986264883f589341d136178fd6d34f5f597de03","target":"record","created_at":"2026-07-05T10:35:32Z","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":"c110feaa3099cf061cfef7efb381756bbe5b7006de764b764a3017eadb88b8c9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T17:14:00Z","title_canon_sha256":"b2c2d9e03dda579ff004073863c9757d0f2d664dac275d8bb3fa5c5d089787ba"},"schema_version":"1.0","source":{"id":"2403.16952","kind":"arxiv","version":2}},"canonical_sha256":"93858a8df4efa977f9fcd784ee8b65e405190a7b2254e284b79c269735f92586","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93858a8df4efa977f9fcd784ee8b65e405190a7b2254e284b79c269735f92586","first_computed_at":"2026-07-05T10:35:32.077756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:32.077756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GBiO/wLjWZse+U5tyZeqi3ZlKDZ20PNfnLo/xstzmqZ5lW4CPGL8t7ZtI8KNXEIJiTFLPoiAdKaCMhZBautEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:32.078776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16952","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97fc49813b8b585ee255f86f6986264883f589341d136178fd6d34f5f597de03","sha256:4f27c31e278169af06716452a3ac7dce64b0ec64ced682ca900a7c16d5cc2860"],"state_sha256":"9f2f4e8cd13c9f0bd41d96c8daac4508eede8c27fc4d2e09a23192382438eb27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0/yZd2C3YWwjSlZqO8AqeRulXN9lndzQIiFBuyphLprObK27ZfzfRi/ONkHLan0HofQN1xOV8+DqsnlhJ9X+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:15:30.053938Z","bundle_sha256":"d62f98b65149f60a48025d35651e918eb3a5c2e3d3558aeae61eab47ded3e4be"}}