{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WDBS3BETC4KYHA5Q5P2ETJQOVE","short_pith_number":"pith:WDBS3BET","schema_version":"1.0","canonical_sha256":"b0c32d849317158383b0ebf449a60ea92d0d5dc847113314fde81b9c181c3aee","source":{"kind":"arxiv","id":"2606.07778","version":1},"attestation_state":"computed","paper":{"title":"Unlocking Latent Value: Taxonomy-Guided Recovery of High-Performing Data from Low-Tier Web Corpora","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Yin, Nasser Zalmout, Neeraj Varshney, Priyanka Nigam, Qingyu Yin, Sanket Lokegaonkar","submitted_at":"2026-06-05T18:43:14Z","abstract_excerpt":"Dominant web data curation pipelines for pretraining collapse document quality into a single composite score, systematically missing high-value content along dimensions the scorer underweights. We present a taxonomy-driven framework that recovers this value by filtering along semantically meaningful dimensions that composite scores fail to capture. First, building on the ESSENTIAL-WEB taxonomy, we introduce two novel dimensions: timeliness and cultural specificity, both of which show low pairwise NMI with existing ones. We annotate 14M documents using Qwen2.5 32B and distill into a lightweight"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.07778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T18:43:14Z","cross_cats_sorted":[],"title_canon_sha256":"4888961fefd540ae0fb5fb73380188e6a4c6c3dc557e8c71e5c2d880cea40e28","abstract_canon_sha256":"1488962be67fca76711e28a22f715302b35a59acee9ee354b876bf4c144f5c23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:51.999127Z","signature_b64":"/QDcYQmZcaorKSflWaZJZ0p93HXUG39o/eWsSFntDuNmvRTd+w9IRzuR+Hwv20WXkwhkcgKU1r5ktAAhQQ4uAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c32d849317158383b0ebf449a60ea92d0d5dc847113314fde81b9c181c3aee","last_reissued_at":"2026-06-09T01:04:51.998692Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:51.998692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Latent Value: Taxonomy-Guided Recovery of High-Performing Data from Low-Tier Web Corpora","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Yin, Nasser Zalmout, Neeraj Varshney, Priyanka Nigam, Qingyu Yin, Sanket Lokegaonkar","submitted_at":"2026-06-05T18:43:14Z","abstract_excerpt":"Dominant web data curation pipelines for pretraining collapse document quality into a single composite score, systematically missing high-value content along dimensions the scorer underweights. We present a taxonomy-driven framework that recovers this value by filtering along semantically meaningful dimensions that composite scores fail to capture. First, building on the ESSENTIAL-WEB taxonomy, we introduce two novel dimensions: timeliness and cultural specificity, both of which show low pairwise NMI with existing ones. We annotate 14M documents using Qwen2.5 32B and distill into a lightweight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07778","kind":"arxiv","version":1},"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/2606.07778/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.07778","created_at":"2026-06-09T01:04:51.998759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07778v1","created_at":"2026-06-09T01:04:51.998759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07778","created_at":"2026-06-09T01:04:51.998759+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDBS3BETC4KY","created_at":"2026-06-09T01:04:51.998759+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDBS3BETC4KYHA5Q","created_at":"2026-06-09T01:04:51.998759+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDBS3BET","created_at":"2026-06-09T01:04:51.998759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE","json":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE.json","graph_json":"https://pith.science/api/pith-number/WDBS3BETC4KYHA5Q5P2ETJQOVE/graph.json","events_json":"https://pith.science/api/pith-number/WDBS3BETC4KYHA5Q5P2ETJQOVE/events.json","paper":"https://pith.science/paper/WDBS3BET"},"agent_actions":{"view_html":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE","download_json":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE.json","view_paper":"https://pith.science/paper/WDBS3BET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07778&json=true","fetch_graph":"https://pith.science/api/pith-number/WDBS3BETC4KYHA5Q5P2ETJQOVE/graph.json","fetch_events":"https://pith.science/api/pith-number/WDBS3BETC4KYHA5Q5P2ETJQOVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/action/storage_attestation","attest_author":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/action/author_attestation","sign_citation":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/action/citation_signature","submit_replication":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/action/replication_record"}},"created_at":"2026-06-09T01:04:51.998759+00:00","updated_at":"2026-06-09T01:04:51.998759+00:00"}