{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UOJQ4WG3WSEB5VPTM76PJTREDE","short_pith_number":"pith:UOJQ4WG3","schema_version":"1.0","canonical_sha256":"a3930e58dbb4881ed5f367fcf4ce241923e9e8be0c7185afa428fbe15d5b708a","source":{"kind":"arxiv","id":"2506.03822","version":1},"attestation_state":"computed","paper":{"title":"CRAWLDoc: A Dataset for Robust Ranking of Bibliographic Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ansgar Scherp, Fabian Karl","submitted_at":"2025-06-04T10:52:55Z","abstract_excerpt":"Publication databases rely on accurate metadata extraction from diverse web sources, yet variations in web layouts and data formats present challenges for metadata providers. This paper introduces CRAWLDoc, a new method for contextual ranking of linked web documents. Starting with a publication's URL, such as a digital object identifier, CRAWLDoc retrieves the landing page and all linked web resources, including PDFs, ORCID profiles, and supplementary materials. It embeds these resources, along with anchor texts and the URLs, into a unified representation. For evaluating CRAWLDoc, we have crea"},"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":"2506.03822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T10:52:55Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d49a6e581388a084ddc13fec3cf6bd03b24e15da0504ef7263de30d264e656dc","abstract_canon_sha256":"6230574864bcc4ce37359faf5624924f1dc12440793140b8923607c5a350f003"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:52.390107Z","signature_b64":"DY+sQKw6O7JFBY1Sp4zILbI2AvvnSQ3udARxpgnbhUoGpJqMOFN5BMOeGUNoLsWyAsT4u/BQpOOVpBgBrIJ2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3930e58dbb4881ed5f367fcf4ce241923e9e8be0c7185afa428fbe15d5b708a","last_reissued_at":"2026-07-05T11:15:52.389732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:52.389732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRAWLDoc: A Dataset for Robust Ranking of Bibliographic Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ansgar Scherp, Fabian Karl","submitted_at":"2025-06-04T10:52:55Z","abstract_excerpt":"Publication databases rely on accurate metadata extraction from diverse web sources, yet variations in web layouts and data formats present challenges for metadata providers. This paper introduces CRAWLDoc, a new method for contextual ranking of linked web documents. Starting with a publication's URL, such as a digital object identifier, CRAWLDoc retrieves the landing page and all linked web resources, including PDFs, ORCID profiles, and supplementary materials. It embeds these resources, along with anchor texts and the URLs, into a unified representation. For evaluating CRAWLDoc, we have crea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03822","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/2506.03822/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":"2506.03822","created_at":"2026-07-05T11:15:52.389802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03822v1","created_at":"2026-07-05T11:15:52.389802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03822","created_at":"2026-07-05T11:15:52.389802+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOJQ4WG3WSEB","created_at":"2026-07-05T11:15:52.389802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOJQ4WG3WSEB5VPT","created_at":"2026-07-05T11:15:52.389802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOJQ4WG3","created_at":"2026-07-05T11:15:52.389802+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/UOJQ4WG3WSEB5VPTM76PJTREDE","json":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE.json","graph_json":"https://pith.science/api/pith-number/UOJQ4WG3WSEB5VPTM76PJTREDE/graph.json","events_json":"https://pith.science/api/pith-number/UOJQ4WG3WSEB5VPTM76PJTREDE/events.json","paper":"https://pith.science/paper/UOJQ4WG3"},"agent_actions":{"view_html":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE","download_json":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE.json","view_paper":"https://pith.science/paper/UOJQ4WG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03822&json=true","fetch_graph":"https://pith.science/api/pith-number/UOJQ4WG3WSEB5VPTM76PJTREDE/graph.json","fetch_events":"https://pith.science/api/pith-number/UOJQ4WG3WSEB5VPTM76PJTREDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/action/storage_attestation","attest_author":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/action/author_attestation","sign_citation":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/action/citation_signature","submit_replication":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/action/replication_record"}},"created_at":"2026-07-05T11:15:52.389802+00:00","updated_at":"2026-07-05T11:15:52.389802+00:00"}