{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5HWQAOF7PVQHQOGFHYK3MBQDVL","short_pith_number":"pith:5HWQAOF7","schema_version":"1.0","canonical_sha256":"e9ed0038bf7d607838c53e15b60603aae5ff79cf8f5a787d5f10b7e86b7495a1","source":{"kind":"arxiv","id":"2607.21284","version":1},"attestation_state":"computed","paper":{"title":"news-crawler-LM: A Small Long-Context Model For High-Quality News Crawling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Akbik, Jonas Golde, Max Dallabetta, Pascal Stolzenburg","submitted_at":"2026-07-23T13:05:46Z","abstract_excerpt":"Extracting structured content from news pages remains challenging due to heterogeneous HTML layouts, inconsistent markup, and substantial boilerplate such as navigation elements and advertisements. Rule-based news crawlers can achieve high extraction accuracy by encoding site-specific structure, but require manual configuration in order to generalize to new publishers. Large language models provide a more flexible alternative by reducing the need for handcrafted rules, but their high computational cost limits practical deployment. In this paper, we introduce news-crawler-LM, a small long-conte"},"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":"2607.21284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T13:05:46Z","cross_cats_sorted":[],"title_canon_sha256":"e6d1e8b01a29bd1f47009bed2afe7ab711d2866ca5f4cb43f5193015af81a651","abstract_canon_sha256":"bf7d311a14d1848ba699ad9ee0bc42692c731597095b1f2b68cce85aa05903af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:23.576652Z","signature_b64":"YDi1jChUDb2Rj/e/4hAYY1nG42unZlkZm0SncavOBDChE1LLal3lBpgfLXEHPd4t93qIIFrRANf6uqBFxADVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ed0038bf7d607838c53e15b60603aae5ff79cf8f5a787d5f10b7e86b7495a1","last_reissued_at":"2026-07-24T01:24:23.575722Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:23.575722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"news-crawler-LM: A Small Long-Context Model For High-Quality News Crawling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Akbik, Jonas Golde, Max Dallabetta, Pascal Stolzenburg","submitted_at":"2026-07-23T13:05:46Z","abstract_excerpt":"Extracting structured content from news pages remains challenging due to heterogeneous HTML layouts, inconsistent markup, and substantial boilerplate such as navigation elements and advertisements. Rule-based news crawlers can achieve high extraction accuracy by encoding site-specific structure, but require manual configuration in order to generalize to new publishers. Large language models provide a more flexible alternative by reducing the need for handcrafted rules, but their high computational cost limits practical deployment. In this paper, we introduce news-crawler-LM, a small long-conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21284","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/2607.21284/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":"2607.21284","created_at":"2026-07-24T01:24:23.576200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21284v1","created_at":"2026-07-24T01:24:23.576200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21284","created_at":"2026-07-24T01:24:23.576200+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HWQAOF7PVQH","created_at":"2026-07-24T01:24:23.576200+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HWQAOF7PVQHQOGF","created_at":"2026-07-24T01:24:23.576200+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HWQAOF7","created_at":"2026-07-24T01:24:23.576200+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/5HWQAOF7PVQHQOGFHYK3MBQDVL","json":"https://pith.science/pith/5HWQAOF7PVQHQOGFHYK3MBQDVL.json","graph_json":"https://pith.science/api/pith-number/5HWQAOF7PVQHQOGFHYK3MBQDVL/graph.json","events_json":"https://pith.science/api/pith-number/5HWQAOF7PVQHQOGFHYK3MBQDVL/events.json","paper":"https://pith.science/paper/5HWQAOF7"},"agent_actions":{"view_html":"https://pith.science/pith/5HWQAOF7PVQHQOGFHYK3MBQDVL","download_json":"https://pith.science/pith/5HWQAOF7PVQHQOGFHYK3MBQDVL.json","view_paper":"https://pith.science/paper/5HWQAOF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21284&json=true","fetch_graph":"https://pith.science/api/pith-number/5HWQAOF7PVQHQOGFHYK3MBQDVL/graph.json","fetch_events":"https://pith.science/api/pith-number/5HWQAOF7PVQHQOGFHYK3MBQDVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HWQAOF7PVQHQOGFHYK3MBQDVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HWQAOF7PVQHQOGFHYK3MBQDVL/action/storage_attestation","attest_author":"https://pith.science/pith/5HWQAOF7PVQHQOGFHYK3MBQDVL/action/author_attestation","sign_citation":"https://pith.science/pith/5HWQAOF7PVQHQOGFHYK3MBQDVL/action/citation_signature","submit_replication":"https://pith.science/pith/5HWQAOF7PVQHQOGFHYK3MBQDVL/action/replication_record"}},"created_at":"2026-07-24T01:24:23.576200+00:00","updated_at":"2026-07-24T01:24:23.576200+00:00"}