{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2RO4S7UC22DJ2IJGGJLGMNB5IM","short_pith_number":"pith:2RO4S7UC","canonical_record":{"source":{"id":"2502.00761","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T11:52:26Z","cross_cats_sorted":[],"title_canon_sha256":"5455c10e6413b5b978dca6ccb4b4ed9fb3ed1929f8334f61966d50e8473b197e","abstract_canon_sha256":"1a3adc5564d94b0460bc73e08e514413ac3db9f384f037ec4fb9a7ea4ad2ad3e"},"schema_version":"1.0"},"canonical_sha256":"d45dc97e82d6869d2126325666343d4328087411e085c1fe93fd5ffeae618ff3","source":{"kind":"arxiv","id":"2502.00761","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00761","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00761v3","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00761","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_12","alias_value":"2RO4S7UC22DJ","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_16","alias_value":"2RO4S7UC22DJ2IJG","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_8","alias_value":"2RO4S7UC","created_at":"2026-07-05T11:07:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2RO4S7UC22DJ2IJGGJLGMNB5IM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.00761","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T11:52:26Z","cross_cats_sorted":[],"title_canon_sha256":"5455c10e6413b5b978dca6ccb4b4ed9fb3ed1929f8334f61966d50e8473b197e","abstract_canon_sha256":"1a3adc5564d94b0460bc73e08e514413ac3db9f384f037ec4fb9a7ea4ad2ad3e"},"schema_version":"1.0"},"canonical_sha256":"d45dc97e82d6869d2126325666343d4328087411e085c1fe93fd5ffeae618ff3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:19.848030Z","signature_b64":"lsGAxcIuF483vOfzL52UUg7sbMVPyXG7ihxyj4w+Vz9MoL1Np/RVWYO7UYiOsxUhpoWkts+6l95gKIOCULHLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d45dc97e82d6869d2126325666343d4328087411e085c1fe93fd5ffeae618ff3","last_reissued_at":"2026-07-05T11:07:19.847568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:19.847568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.00761","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":"2026-07-05T11:07:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M01MLV1NGW6mV4hAdLhGuHdo2SILDUR2ujGbrs2SQ77nx/XptKSXsU1LLjjlo7qZUHZJY/u+pqaTG48umgoUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:32:13.720127Z"},"content_sha256":"9877d7429581c7cb8132d150269b8069a22b21140789d90871a9fc84f56f6c6b","schema_version":"1.0","event_id":"sha256:9877d7429581c7cb8132d150269b8069a22b21140789d90871a9fc84f56f6c6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2RO4S7UC22DJ2IJGGJLGMNB5IM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FIRE: Flexible Integration of Data Quality Ratings for Effective Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feiyu Duan, Jingang Wang, Liangyu Xu, Rongxiang Weng, Sirui Wang, Xuemiao Zhang, Xunliang Cai","submitted_at":"2025-02-02T11:52:26Z","abstract_excerpt":"Selecting high-quality data can improve the pretraining efficiency of large language models (LLMs). Existing methods generally rely on heuristic techniques or single quality signals, limiting their ability to evaluate data quality comprehensively. In this work, we propose FIRE, a flexible and scalable framework for integrating multiple data quality raters, which allows for a comprehensive assessment of data quality across various dimensions. FIRE aligns multiple quality signals into a unified space, and integrates diverse data quality raters to provide a comprehensive quality signal for each d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00761","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/2502.00761/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":"2026-07-05T11:07:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5XTHaFfczGvuvu7w0d7WFsK/RkDaqjMqG+S2xQcK0Knl28Om8yYhj+kFpqxynvP2Tw5dYohhTfZuF4uFb4p/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:32:13.720595Z"},"content_sha256":"f2f0256ab7d8c365375ef87153d389b749231f34626ece5fff387070274d5001","schema_version":"1.0","event_id":"sha256:f2f0256ab7d8c365375ef87153d389b749231f34626ece5fff387070274d5001"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2RO4S7UC22DJ2IJGGJLGMNB5IM/bundle.json","state_url":"https://pith.science/pith/2RO4S7UC22DJ2IJGGJLGMNB5IM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2RO4S7UC22DJ2IJGGJLGMNB5IM/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":"2026-07-07T05:32:13Z","links":{"resolver":"https://pith.science/pith/2RO4S7UC22DJ2IJGGJLGMNB5IM","bundle":"https://pith.science/pith/2RO4S7UC22DJ2IJGGJLGMNB5IM/bundle.json","state":"https://pith.science/pith/2RO4S7UC22DJ2IJGGJLGMNB5IM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2RO4S7UC22DJ2IJGGJLGMNB5IM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2RO4S7UC22DJ2IJGGJLGMNB5IM","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":"1a3adc5564d94b0460bc73e08e514413ac3db9f384f037ec4fb9a7ea4ad2ad3e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T11:52:26Z","title_canon_sha256":"5455c10e6413b5b978dca6ccb4b4ed9fb3ed1929f8334f61966d50e8473b197e"},"schema_version":"1.0","source":{"id":"2502.00761","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00761","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00761v3","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00761","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_12","alias_value":"2RO4S7UC22DJ","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_16","alias_value":"2RO4S7UC22DJ2IJG","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_8","alias_value":"2RO4S7UC","created_at":"2026-07-05T11:07:19Z"}],"graph_snapshots":[{"event_id":"sha256:f2f0256ab7d8c365375ef87153d389b749231f34626ece5fff387070274d5001","target":"graph","created_at":"2026-07-05T11:07:19Z","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/2502.00761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Selecting high-quality data can improve the pretraining efficiency of large language models (LLMs). Existing methods generally rely on heuristic techniques or single quality signals, limiting their ability to evaluate data quality comprehensively. In this work, we propose FIRE, a flexible and scalable framework for integrating multiple data quality raters, which allows for a comprehensive assessment of data quality across various dimensions. FIRE aligns multiple quality signals into a unified space, and integrates diverse data quality raters to provide a comprehensive quality signal for each d","authors_text":"Feiyu Duan, Jingang Wang, Liangyu Xu, Rongxiang Weng, Sirui Wang, Xuemiao Zhang, Xunliang Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T11:52:26Z","title":"FIRE: Flexible Integration of Data Quality Ratings for Effective Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00761","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":"sha256:9877d7429581c7cb8132d150269b8069a22b21140789d90871a9fc84f56f6c6b","target":"record","created_at":"2026-07-05T11:07:19Z","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":"1a3adc5564d94b0460bc73e08e514413ac3db9f384f037ec4fb9a7ea4ad2ad3e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T11:52:26Z","title_canon_sha256":"5455c10e6413b5b978dca6ccb4b4ed9fb3ed1929f8334f61966d50e8473b197e"},"schema_version":"1.0","source":{"id":"2502.00761","kind":"arxiv","version":3}},"canonical_sha256":"d45dc97e82d6869d2126325666343d4328087411e085c1fe93fd5ffeae618ff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d45dc97e82d6869d2126325666343d4328087411e085c1fe93fd5ffeae618ff3","first_computed_at":"2026-07-05T11:07:19.847568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:19.847568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lsGAxcIuF483vOfzL52UUg7sbMVPyXG7ihxyj4w+Vz9MoL1Np/RVWYO7UYiOsxUhpoWkts+6l95gKIOCULHLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:19.848030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00761","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9877d7429581c7cb8132d150269b8069a22b21140789d90871a9fc84f56f6c6b","sha256:f2f0256ab7d8c365375ef87153d389b749231f34626ece5fff387070274d5001"],"state_sha256":"a56d8c777c553149ece50b88d2cf9602b08702ff653a486656c99b908b379589"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EgDX3g9U8XT+DIRiLBZCwzBDdRlRKkT5WQbhCjjXYjG398UNBXK2XLqIXtyRbywmkHVpM52atzpIquwnGLhWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:32:13.723572Z","bundle_sha256":"5ba743161657560c3f026e122b88397f280f81d11f4685801bf2d79fd2a685c5"}}