{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B563JTAYOFBILA3HLLH647WUQX","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":"8dc3a14f071e4e68404da95673e4f7329b5721b842c6a75a33534abf8370bc87","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T13:09:21Z","title_canon_sha256":"02ae2f6d86ed4ac00ad5e89ba83c9c99b90a882773fa6b2327d3ba04fbe315c3"},"schema_version":"1.0","source":{"id":"2402.07625","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07625","created_at":"2026-07-05T11:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07625v7","created_at":"2026-07-05T11:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07625","created_at":"2026-07-05T11:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"B563JTAYOFBI","created_at":"2026-07-05T11:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"B563JTAYOFBILA3H","created_at":"2026-07-05T11:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"B563JTAY","created_at":"2026-07-05T11:40:47Z"}],"graph_snapshots":[{"event_id":"sha256:9c389e17896e6b6933c21c33edc54105ea7c0cdc6de2bff3dbd5c91abb18018a","target":"graph","created_at":"2026-07-05T11:40:47Z","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/2402.07625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Autonomous Data Selection (AutoDS), a method that leverages base language models themselves as zero-shot \"generative classifiers\" to automatically curate high-quality mathematical texts. Unlike prior approaches that require human annotations or training a dedicated data filter, AutoDS relies solely on a model's logits to determine whether a given passage is mathematically informative and educational. By integrating AutoDS into a continual pretraining pipeline, we substantially boost downstream performance on challenging math benchmarks (MATH, GSM8K, and BBH) while using far fewer to","authors_text":"Andrew C Yao, Yang Yuan, Yifan Luo, Yifan Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T13:09:21Z","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07625","kind":"arxiv","version":7},"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":"sha256:06f1e24918bd34ea183bbaa508ee4096d1caa1f20bf0e4b31ced713b23eeb88a","target":"record","created_at":"2026-07-05T11:40:47Z","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":"8dc3a14f071e4e68404da95673e4f7329b5721b842c6a75a33534abf8370bc87","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T13:09:21Z","title_canon_sha256":"02ae2f6d86ed4ac00ad5e89ba83c9c99b90a882773fa6b2327d3ba04fbe315c3"},"schema_version":"1.0","source":{"id":"2402.07625","kind":"arxiv","version":7}},"canonical_sha256":"0f7db4cc1871428583675acfee7ed485dda1fd3b84f5eb81cc13ba54492ecfd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f7db4cc1871428583675acfee7ed485dda1fd3b84f5eb81cc13ba54492ecfd9","first_computed_at":"2026-07-05T11:40:47.705931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:47.705931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p6yeJ4szfNkXwNft9dBv5r0rhVdM350+wfSkwbRodLMwilIzl+r/G77tneiwrGjZZvcLPu7yB4kJ9BOv++UvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:47.706491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07625","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06f1e24918bd34ea183bbaa508ee4096d1caa1f20bf0e4b31ced713b23eeb88a","sha256:9c389e17896e6b6933c21c33edc54105ea7c0cdc6de2bff3dbd5c91abb18018a"],"state_sha256":"0a26c296c5b90b602c81a013405daab3e8aaa7add021cb200ccd1d102b1b8903"}