{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JPRDV4QHUEAPVQKEJCZOBNESYG","short_pith_number":"pith:JPRDV4QH","schema_version":"1.0","canonical_sha256":"4be23af207a100fac14448b2e0b492c18d89cdbd743e702a7ae8f60086d94328","source":{"kind":"arxiv","id":"2605.21097","version":1},"attestation_state":"computed","paper":{"title":"WCXB: A Multi-Type Web Content Extraction Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Murrough Foley","submitted_at":"2026-05-20T12:28:12Z","abstract_excerpt":"Web content extraction - isolating a page's main content from surrounding boilerplate - is a prerequisite for search indexing, retrieval-augmented generation, NLP dataset construction, and large language model training. Progress in this area has been constrained by the limitations of existing evaluation benchmarks, which are small (100-800 pages), restricted to news articles, or based on web pages from over a decade ago. We introduce the Web Content Extraction Benchmark (WCXB), a dataset of 2,008 web pages from 1,613 domains spanning seven structurally distinct page types: articles, forums, pr"},"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":"2605.21097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T12:28:12Z","cross_cats_sorted":[],"title_canon_sha256":"dd839f4287d20e16e530f6af607a6cff410530afeeaf73d4c101824a186eddf1","abstract_canon_sha256":"cc75da1300bb3172ed52aa160d11437d0cb56e3f3c83b4c48f3a26da2d19631d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:37.013918Z","signature_b64":"jjv6gwLRLf5XJ4a8KhZ26hpJWtCA8DKgGEcYzLuOvWalA77WaVtv3IB8jHQiZ2aAtneYaqtRrCNxMDQusH0zCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4be23af207a100fac14448b2e0b492c18d89cdbd743e702a7ae8f60086d94328","last_reissued_at":"2026-05-21T01:05:37.013213Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:37.013213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WCXB: A Multi-Type Web Content Extraction Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Murrough Foley","submitted_at":"2026-05-20T12:28:12Z","abstract_excerpt":"Web content extraction - isolating a page's main content from surrounding boilerplate - is a prerequisite for search indexing, retrieval-augmented generation, NLP dataset construction, and large language model training. Progress in this area has been constrained by the limitations of existing evaluation benchmarks, which are small (100-800 pages), restricted to news articles, or based on web pages from over a decade ago. We introduce the Web Content Extraction Benchmark (WCXB), a dataset of 2,008 web pages from 1,613 domains spanning seven structurally distinct page types: articles, forums, pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21097","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/2605.21097/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":"2605.21097","created_at":"2026-05-21T01:05:37.013309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21097v1","created_at":"2026-05-21T01:05:37.013309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21097","created_at":"2026-05-21T01:05:37.013309+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPRDV4QHUEAP","created_at":"2026-05-21T01:05:37.013309+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPRDV4QHUEAPVQKE","created_at":"2026-05-21T01:05:37.013309+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPRDV4QH","created_at":"2026-05-21T01:05:37.013309+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/JPRDV4QHUEAPVQKEJCZOBNESYG","json":"https://pith.science/pith/JPRDV4QHUEAPVQKEJCZOBNESYG.json","graph_json":"https://pith.science/api/pith-number/JPRDV4QHUEAPVQKEJCZOBNESYG/graph.json","events_json":"https://pith.science/api/pith-number/JPRDV4QHUEAPVQKEJCZOBNESYG/events.json","paper":"https://pith.science/paper/JPRDV4QH"},"agent_actions":{"view_html":"https://pith.science/pith/JPRDV4QHUEAPVQKEJCZOBNESYG","download_json":"https://pith.science/pith/JPRDV4QHUEAPVQKEJCZOBNESYG.json","view_paper":"https://pith.science/paper/JPRDV4QH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21097&json=true","fetch_graph":"https://pith.science/api/pith-number/JPRDV4QHUEAPVQKEJCZOBNESYG/graph.json","fetch_events":"https://pith.science/api/pith-number/JPRDV4QHUEAPVQKEJCZOBNESYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPRDV4QHUEAPVQKEJCZOBNESYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPRDV4QHUEAPVQKEJCZOBNESYG/action/storage_attestation","attest_author":"https://pith.science/pith/JPRDV4QHUEAPVQKEJCZOBNESYG/action/author_attestation","sign_citation":"https://pith.science/pith/JPRDV4QHUEAPVQKEJCZOBNESYG/action/citation_signature","submit_replication":"https://pith.science/pith/JPRDV4QHUEAPVQKEJCZOBNESYG/action/replication_record"}},"created_at":"2026-05-21T01:05:37.013309+00:00","updated_at":"2026-05-21T01:05:37.013309+00:00"}