{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WDBS3BETC4KYHA5Q5P2ETJQOVE","short_pith_number":"pith:WDBS3BET","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"},"canonical_sha256":"b0c32d849317158383b0ebf449a60ea92d0d5dc847113314fde81b9c181c3aee","source":{"kind":"arxiv","id":"2606.07778","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07778","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07778v1","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07778","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"WDBS3BETC4KY","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"WDBS3BETC4KYHA5Q","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"WDBS3BET","created_at":"2026-06-09T01:04:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WDBS3BETC4KYHA5Q5P2ETJQOVE","target":"record","payload":{"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"},"canonical_sha256":"b0c32d849317158383b0ebf449a60ea92d0d5dc847113314fde81b9c181c3aee","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"},"source_kind":"arxiv","source_id":"2606.07778","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eS9/Sf2pZKJE1hiFTopJcsGNvj7BHFw0QpIWrQ5LU0qtJlCumBEl7KCys/JgvKt3NpxNmOim4DdQ1v5VRFF6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T06:12:40.102957Z"},"content_sha256":"a0abc65de0cd4f3444c0e959d9f71a092798797f6b5c3e480244e86e4f6b3c61","schema_version":"1.0","event_id":"sha256:a0abc65de0cd4f3444c0e959d9f71a092798797f6b5c3e480244e86e4f6b3c61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WDBS3BETC4KYHA5Q5P2ETJQOVE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jxgboui87vudhAffvKu+2P+8sk989VboRaMLN8f5Hl2q04QqPReUkqH9UnELRR6XnhKriC5vFP9hkd7THskkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T06:12:40.103349Z"},"content_sha256":"8872ca19fa2040e2c8ba3063eaf9cad32d38c930491fdf1f25cd838d24b5f6da","schema_version":"1.0","event_id":"sha256:8872ca19fa2040e2c8ba3063eaf9cad32d38c930491fdf1f25cd838d24b5f6da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/bundle.json","state_url":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/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":"2026-07-03T06:12:40Z","links":{"resolver":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE","bundle":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/bundle.json","state":"https://pith.science/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WDBS3BETC4KYHA5Q5P2ETJQOVE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WDBS3BETC4KYHA5Q5P2ETJQOVE","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":"1488962be67fca76711e28a22f715302b35a59acee9ee354b876bf4c144f5c23","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T18:43:14Z","title_canon_sha256":"4888961fefd540ae0fb5fb73380188e6a4c6c3dc557e8c71e5c2d880cea40e28"},"schema_version":"1.0","source":{"id":"2606.07778","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07778","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07778v1","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07778","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"WDBS3BETC4KY","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"WDBS3BETC4KYHA5Q","created_at":"2026-06-09T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"WDBS3BET","created_at":"2026-06-09T01:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:8872ca19fa2040e2c8ba3063eaf9cad32d38c930491fdf1f25cd838d24b5f6da","target":"graph","created_at":"2026-06-09T01:04:51Z","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/2606.07778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bing Yin, Nasser Zalmout, Neeraj Varshney, Priyanka Nigam, Qingyu Yin, Sanket Lokegaonkar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T18:43:14Z","title":"Unlocking Latent Value: Taxonomy-Guided Recovery of High-Performing Data from Low-Tier Web Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07778","kind":"arxiv","version":1},"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:a0abc65de0cd4f3444c0e959d9f71a092798797f6b5c3e480244e86e4f6b3c61","target":"record","created_at":"2026-06-09T01:04:51Z","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":"1488962be67fca76711e28a22f715302b35a59acee9ee354b876bf4c144f5c23","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T18:43:14Z","title_canon_sha256":"4888961fefd540ae0fb5fb73380188e6a4c6c3dc557e8c71e5c2d880cea40e28"},"schema_version":"1.0","source":{"id":"2606.07778","kind":"arxiv","version":1}},"canonical_sha256":"b0c32d849317158383b0ebf449a60ea92d0d5dc847113314fde81b9c181c3aee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0c32d849317158383b0ebf449a60ea92d0d5dc847113314fde81b9c181c3aee","first_computed_at":"2026-06-09T01:04:51.998692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:51.998692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/QDcYQmZcaorKSflWaZJZ0p93HXUG39o/eWsSFntDuNmvRTd+w9IRzuR+Hwv20WXkwhkcgKU1r5ktAAhQQ4uAg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:51.999127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07778","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0abc65de0cd4f3444c0e959d9f71a092798797f6b5c3e480244e86e4f6b3c61","sha256:8872ca19fa2040e2c8ba3063eaf9cad32d38c930491fdf1f25cd838d24b5f6da"],"state_sha256":"c8ba434bfbfa4115d75121d101e34ea78dbcd86dd9f8de3fd78178229f7155b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8grqV0/8qKujB+R2I+fI64eF2BniEXTwB1Mv3KfKj5cETN9PSncTNtTeKDToCEIYL+nAmsEqzUt/TMIeLq5/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T06:12:40.105381Z","bundle_sha256":"699d812a65ae6cfc43aec0d8e10012899fa08d6635ed633d19be77c9ccb99d69"}}