{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4UJIG5XJBEVWKVBOVMNT7Q3GRE","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":"3a8880e537310e549767412522a1a6d975965c0445493ca39221fe341b94c295","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T08:53:27Z","title_canon_sha256":"6c9cef8cd39128e9e4b2de95b99df439d44824b50babbfcc440c4d22eeaec660"},"schema_version":"1.0","source":{"id":"2505.02851","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02851","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02851v2","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02851","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"4UJIG5XJBEVW","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"4UJIG5XJBEVWKVBO","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"4UJIG5XJ","created_at":"2026-07-05T11:45:57Z"}],"graph_snapshots":[{"event_id":"sha256:9a565d29ea51d8cc08607741a9ecd6b9c5e565a005459d71a2f857f284b8a613","target":"graph","created_at":"2026-07-05T11:45:57Z","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/2505.02851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Constructing specialized content corpora from vast, unstructured web sources for domain-specific applications poses substantial data curation challenges. In this paper, we introduce a streamlined approach for generating high-quality, domain-specific corpora by efficiently acquiring, filtering, structuring, and cleaning web-based data. We showcase how Large Language Models (LLMs) can be leveraged to address complex data curation at scale, and propose a strategical framework incorporating LLM-enhanced techniques for structured content extraction and semantic deduplication. We validate our approa","authors_text":"Alon Halevy, Franklin Zhang, Sonya Zhang","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T08:53:27Z","title":"Leveraging LLMs to Create Content Corpora for Niche Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02851","kind":"arxiv","version":2},"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":"sha256:51de3c61e2157ace8f8ee5213bb217d02465cea60dd616c4c02bc63d64ab4f09","target":"record","created_at":"2026-07-05T11:45:57Z","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":"3a8880e537310e549767412522a1a6d975965c0445493ca39221fe341b94c295","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T08:53:27Z","title_canon_sha256":"6c9cef8cd39128e9e4b2de95b99df439d44824b50babbfcc440c4d22eeaec660"},"schema_version":"1.0","source":{"id":"2505.02851","kind":"arxiv","version":2}},"canonical_sha256":"e5128376e9092b65542eab1b3fc366892fc4d8db40864248458dfbf25bac01d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5128376e9092b65542eab1b3fc366892fc4d8db40864248458dfbf25bac01d0","first_computed_at":"2026-07-05T11:45:57.945461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:57.945461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n+5Fmk3kWJGnsWGPlQSMoSAUAqJf7WImnevBAMOP7MivcPq9h1qHdCg0dp0WUviSHe59dpFcAZjh4t6B9jLbBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:57.946006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02851","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51de3c61e2157ace8f8ee5213bb217d02465cea60dd616c4c02bc63d64ab4f09","sha256:9a565d29ea51d8cc08607741a9ecd6b9c5e565a005459d71a2f857f284b8a613"],"state_sha256":"b3affb5a1e91e3380dbad60c5d99daef93f357a8fbe8181a5ca10fc088b49158"}