{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KCZQIXIOAZJ6MFKH3APJHCUY66","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":"6f1f0fb51774e2d1f46c8fa1c63bcf48c816d771d3483f13e6e7d23c940a4718","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T16:33:41Z","title_canon_sha256":"0d7c35329e0117af3994fb15dfaef573b1464da002902b3cb51cbbda8ce4c250"},"schema_version":"1.0","source":{"id":"2502.19279","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19279","created_at":"2026-07-05T12:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19279v3","created_at":"2026-07-05T12:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19279","created_at":"2026-07-05T12:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"KCZQIXIOAZJ6","created_at":"2026-07-05T12:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"KCZQIXIOAZJ6MFKH","created_at":"2026-07-05T12:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"KCZQIXIO","created_at":"2026-07-05T12:09:13Z"}],"graph_snapshots":[{"event_id":"sha256:68a9fc3c9d302aa5d5701931ace5a4c318ab3581a89c3d428c06026c8d8b76ef","target":"graph","created_at":"2026-07-05T12:09:13Z","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/2502.19279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model heavily depends on high-quality data for optimal performance. Existing approaches rely on manually designed heuristics, the perplexity of existing models, training classifiers, or careful prompt engineering, which require significant expert experience and human annotation effort while introduce biases. We introduce CritiQ, a novel data selection method that automatically mines criteria from human preferences for data quality with only ~30 human-annotated pairs and performs efficient data selection. The main component, CritiQ Flow, employs a manager agent to evolve quality criter","authors_text":"Demin Song, Honglin Guo, Kai Chen, Kai Lv, Qipeng Guo, Qiuyinzhe Zhang, Tao Gui, Tianyi Liang, Xipeng Qiu, Yu Sun, Zhiheng Xi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T16:33:41Z","title":"CritiQ: Mining Data Quality Criteria from Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19279","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:a5333dce831c3f8620bf8e3a7b3fbf3e1b8d8dba302647ae10522fc929c4029e","target":"record","created_at":"2026-07-05T12:09:13Z","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":"6f1f0fb51774e2d1f46c8fa1c63bcf48c816d771d3483f13e6e7d23c940a4718","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T16:33:41Z","title_canon_sha256":"0d7c35329e0117af3994fb15dfaef573b1464da002902b3cb51cbbda8ce4c250"},"schema_version":"1.0","source":{"id":"2502.19279","kind":"arxiv","version":3}},"canonical_sha256":"50b3045d0e0653e61547d81e938a98f7a61d961470beaf9123af61db41bb26c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50b3045d0e0653e61547d81e938a98f7a61d961470beaf9123af61db41bb26c1","first_computed_at":"2026-07-05T12:09:13.604226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:13.604226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S7wiv4ID9irhmYxgKtziIO5bepJFYpSfVFZwaIAzQRYuWi+MK4CCH3OJkBJPdX3/WTkVvKeT2kRQuowzUQ2+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:13.604763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19279","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5333dce831c3f8620bf8e3a7b3fbf3e1b8d8dba302647ae10522fc929c4029e","sha256:68a9fc3c9d302aa5d5701931ace5a4c318ab3581a89c3d428c06026c8d8b76ef"],"state_sha256":"aeb45926d650ec3b8f8f8360a71dfc5eaa7a1104e0c82bc5ead3b0c2ec4a1d26"}