{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5HWQAOF7PVQHQOGFHYK3MBQDVL","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":"bf7d311a14d1848ba699ad9ee0bc42692c731597095b1f2b68cce85aa05903af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T13:05:46Z","title_canon_sha256":"e6d1e8b01a29bd1f47009bed2afe7ab711d2866ca5f4cb43f5193015af81a651"},"schema_version":"1.0","source":{"id":"2607.21284","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21284","created_at":"2026-07-24T01:24:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21284v1","created_at":"2026-07-24T01:24:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21284","created_at":"2026-07-24T01:24:23Z"},{"alias_kind":"pith_short_12","alias_value":"5HWQAOF7PVQH","created_at":"2026-07-24T01:24:23Z"},{"alias_kind":"pith_short_16","alias_value":"5HWQAOF7PVQHQOGF","created_at":"2026-07-24T01:24:23Z"},{"alias_kind":"pith_short_8","alias_value":"5HWQAOF7","created_at":"2026-07-24T01:24:23Z"}],"graph_snapshots":[{"event_id":"sha256:fcdf61da5520988c1539e8509c2a790eff9cea5c4994580a1672bbf08e9690da","target":"graph","created_at":"2026-07-24T01:24:23Z","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/2607.21284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alan Akbik, Jonas Golde, Max Dallabetta, Pascal Stolzenburg","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T13:05:46Z","title":"news-crawler-LM: A Small Long-Context Model For High-Quality News Crawling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21284","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:bb12c97fc8a4ed8f28509ff5d62e8fd0bbbe7f10e40e322f32f919b5a72d6a79","target":"record","created_at":"2026-07-24T01:24:23Z","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":"bf7d311a14d1848ba699ad9ee0bc42692c731597095b1f2b68cce85aa05903af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T13:05:46Z","title_canon_sha256":"e6d1e8b01a29bd1f47009bed2afe7ab711d2866ca5f4cb43f5193015af81a651"},"schema_version":"1.0","source":{"id":"2607.21284","kind":"arxiv","version":1}},"canonical_sha256":"e9ed0038bf7d607838c53e15b60603aae5ff79cf8f5a787d5f10b7e86b7495a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9ed0038bf7d607838c53e15b60603aae5ff79cf8f5a787d5f10b7e86b7495a1","first_computed_at":"2026-07-24T01:24:23.575722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:24:23.575722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YDi1jChUDb2Rj/e/4hAYY1nG42unZlkZm0SncavOBDChE1LLal3lBpgfLXEHPd4t93qIIFrRANf6uqBFxADVDw==","signature_status":"signed_v1","signed_at":"2026-07-24T01:24:23.576652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21284","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb12c97fc8a4ed8f28509ff5d62e8fd0bbbe7f10e40e322f32f919b5a72d6a79","sha256:fcdf61da5520988c1539e8509c2a790eff9cea5c4994580a1672bbf08e9690da"],"state_sha256":"27193ab7e7dfc3ee71a1e0e95ad775b58f615918da397f96ded712e709b4f6b2"}