{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LOIXRSKSUXJNJRKR2AGJJTVWGV","short_pith_number":"pith:LOIXRSKS","canonical_record":{"source":{"id":"2501.11747","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T21:10:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d07b3388a046460d4b0ff2c9f1dc458ef1bf18e61868e43603e6fbdba489dbb9","abstract_canon_sha256":"2fe64aeae756bf581327e7fe1de00e0b2264dbe74bab397f231b0d3a7ed0e658"},"schema_version":"1.0"},"canonical_sha256":"5b9178c952a5d2d4c551d00c94ceb635498eac0179b4a637e46092addf27a607","source":{"kind":"arxiv","id":"2501.11747","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11747","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11747v2","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11747","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"LOIXRSKSUXJN","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"LOIXRSKSUXJNJRKR","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"LOIXRSKS","created_at":"2026-07-05T10:04:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LOIXRSKSUXJNJRKR2AGJJTVWGV","target":"record","payload":{"canonical_record":{"source":{"id":"2501.11747","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T21:10:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d07b3388a046460d4b0ff2c9f1dc458ef1bf18e61868e43603e6fbdba489dbb9","abstract_canon_sha256":"2fe64aeae756bf581327e7fe1de00e0b2264dbe74bab397f231b0d3a7ed0e658"},"schema_version":"1.0"},"canonical_sha256":"5b9178c952a5d2d4c551d00c94ceb635498eac0179b4a637e46092addf27a607","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:42.014811Z","signature_b64":"sN/dR/BAAgsjimzRpbs5R4xixyW+1XxyFW5KHdVt6Vk7O//zwwSKLQY0SWfzTg0YLXOBAjV7E7ctyplYawtRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b9178c952a5d2d4c551d00c94ceb635498eac0179b4a637e46092addf27a607","last_reissued_at":"2026-07-05T10:04:42.014341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:42.014341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.11747","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":"2026-07-05T10:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OPrsdp8HB9hCEfgvnm4oRnC+fhPRmmvZxlh3DqsvzxmkQrwmaE4waF/AtgpaMB9FaAfqCM7YesgKtRsi9BQDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:44:54.253426Z"},"content_sha256":"f920d649e257a91718e277eae952029179651846a3bb78b681981e0d65ee3caf","schema_version":"1.0","event_id":"sha256:f920d649e257a91718e277eae952029179651846a3bb78b681981e0d65ee3caf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LOIXRSKSUXJNJRKR2AGJJTVWGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Pretraining Data Mixtures with LLM-Estimated Utility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bhargavi Paranjape, Frank Zhang, Mike Lewis, Punit Singh Koura, Todor Mihaylov, William Held","submitted_at":"2025-01-20T21:10:22Z","abstract_excerpt":"Large Language Models improve with increasing amounts of high-quality training data. However, leveraging larger datasets requires balancing quality, quantity, and diversity across sources. After evaluating nine baseline methods under both compute- and data-constrained scenarios, we find token-count heuristics outperform manual and learned mixes, indicating that simple approaches accounting for dataset size and diversity are surprisingly effective. Building on this insight, we propose two complementary approaches: UtiliMax, which extends token-based heuristics by incorporating utility estimates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11747","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/2501.11747/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":"2026-07-05T10:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iq33CpZaD/UokyXPX5QAB3P/qOeCjdgbVRkMItruO8WOMgAABQastw3XiCDwXFUm+a5GYy0AxiwwOS6BkysyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:44:54.253944Z"},"content_sha256":"6190af71875783a5744127d01b941d799a473f2a2a4dbf1cff1aa306b101513f","schema_version":"1.0","event_id":"sha256:6190af71875783a5744127d01b941d799a473f2a2a4dbf1cff1aa306b101513f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOIXRSKSUXJNJRKR2AGJJTVWGV/bundle.json","state_url":"https://pith.science/pith/LOIXRSKSUXJNJRKR2AGJJTVWGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOIXRSKSUXJNJRKR2AGJJTVWGV/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":"2026-08-10T08:44:54Z","links":{"resolver":"https://pith.science/pith/LOIXRSKSUXJNJRKR2AGJJTVWGV","bundle":"https://pith.science/pith/LOIXRSKSUXJNJRKR2AGJJTVWGV/bundle.json","state":"https://pith.science/pith/LOIXRSKSUXJNJRKR2AGJJTVWGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOIXRSKSUXJNJRKR2AGJJTVWGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LOIXRSKSUXJNJRKR2AGJJTVWGV","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":"2fe64aeae756bf581327e7fe1de00e0b2264dbe74bab397f231b0d3a7ed0e658","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T21:10:22Z","title_canon_sha256":"d07b3388a046460d4b0ff2c9f1dc458ef1bf18e61868e43603e6fbdba489dbb9"},"schema_version":"1.0","source":{"id":"2501.11747","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11747","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11747v2","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11747","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"LOIXRSKSUXJN","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"LOIXRSKSUXJNJRKR","created_at":"2026-07-05T10:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"LOIXRSKS","created_at":"2026-07-05T10:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:6190af71875783a5744127d01b941d799a473f2a2a4dbf1cff1aa306b101513f","target":"graph","created_at":"2026-07-05T10:04:42Z","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/2501.11747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models improve with increasing amounts of high-quality training data. However, leveraging larger datasets requires balancing quality, quantity, and diversity across sources. After evaluating nine baseline methods under both compute- and data-constrained scenarios, we find token-count heuristics outperform manual and learned mixes, indicating that simple approaches accounting for dataset size and diversity are surprisingly effective. Building on this insight, we propose two complementary approaches: UtiliMax, which extends token-based heuristics by incorporating utility estimates","authors_text":"Bhargavi Paranjape, Frank Zhang, Mike Lewis, Punit Singh Koura, Todor Mihaylov, William Held","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T21:10:22Z","title":"Optimizing Pretraining Data Mixtures with LLM-Estimated Utility"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11747","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:f920d649e257a91718e277eae952029179651846a3bb78b681981e0d65ee3caf","target":"record","created_at":"2026-07-05T10:04:42Z","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":"2fe64aeae756bf581327e7fe1de00e0b2264dbe74bab397f231b0d3a7ed0e658","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T21:10:22Z","title_canon_sha256":"d07b3388a046460d4b0ff2c9f1dc458ef1bf18e61868e43603e6fbdba489dbb9"},"schema_version":"1.0","source":{"id":"2501.11747","kind":"arxiv","version":2}},"canonical_sha256":"5b9178c952a5d2d4c551d00c94ceb635498eac0179b4a637e46092addf27a607","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b9178c952a5d2d4c551d00c94ceb635498eac0179b4a637e46092addf27a607","first_computed_at":"2026-07-05T10:04:42.014341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:42.014341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sN/dR/BAAgsjimzRpbs5R4xixyW+1XxyFW5KHdVt6Vk7O//zwwSKLQY0SWfzTg0YLXOBAjV7E7ctyplYawtRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:42.014811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11747","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f920d649e257a91718e277eae952029179651846a3bb78b681981e0d65ee3caf","sha256:6190af71875783a5744127d01b941d799a473f2a2a4dbf1cff1aa306b101513f"],"state_sha256":"67a7bb77651e20b429bcb55f37a0824f5ebcec74195ded201ba817d096c680ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L0yldzLducIVpyxgiyksQB5EFpl16j9vcBrjZ3RuZt7IHbm8XUrCd2EAVRFJ9pjT9t2cdeMzUM8Efh7mzeh0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:44:54.259234Z","bundle_sha256":"21856bc7221518d8ddcea1a485420ae133d2a2fb0eedfaf9e4e66468be9433a6"}}