{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4UJIG5XJBEVWKVBOVMNT7Q3GRE","short_pith_number":"pith:4UJIG5XJ","canonical_record":{"source":{"id":"2505.02851","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T08:53:27Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"6c9cef8cd39128e9e4b2de95b99df439d44824b50babbfcc440c4d22eeaec660","abstract_canon_sha256":"3a8880e537310e549767412522a1a6d975965c0445493ca39221fe341b94c295"},"schema_version":"1.0"},"canonical_sha256":"e5128376e9092b65542eab1b3fc366892fc4d8db40864248458dfbf25bac01d0","source":{"kind":"arxiv","id":"2505.02851","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4UJIG5XJBEVWKVBOVMNT7Q3GRE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02851","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T08:53:27Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"6c9cef8cd39128e9e4b2de95b99df439d44824b50babbfcc440c4d22eeaec660","abstract_canon_sha256":"3a8880e537310e549767412522a1a6d975965c0445493ca39221fe341b94c295"},"schema_version":"1.0"},"canonical_sha256":"e5128376e9092b65542eab1b3fc366892fc4d8db40864248458dfbf25bac01d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:57.946006Z","signature_b64":"n+5Fmk3kWJGnsWGPlQSMoSAUAqJf7WImnevBAMOP7MivcPq9h1qHdCg0dp0WUviSHe59dpFcAZjh4t6B9jLbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5128376e9092b65542eab1b3fc366892fc4d8db40864248458dfbf25bac01d0","last_reissued_at":"2026-07-05T11:45:57.945461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:57.945461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02851","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HfdPs/tyYN9ceg6HTqxwbme0hy1J7x6RNWVzROOtpBwjYe8GbZtp74jWD7O2dVl4amW9zelCrXpW8spn3RiFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T16:11:34.133037Z"},"content_sha256":"51de3c61e2157ace8f8ee5213bb217d02465cea60dd616c4c02bc63d64ab4f09","schema_version":"1.0","event_id":"sha256:51de3c61e2157ace8f8ee5213bb217d02465cea60dd616c4c02bc63d64ab4f09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4UJIG5XJBEVWKVBOVMNT7Q3GRE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging LLMs to Create Content Corpora for Niche Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Alon Halevy, Franklin Zhang, Sonya Zhang","submitted_at":"2025-05-02T08:53:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02851","kind":"arxiv","version":2},"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/2505.02851/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AwsB9d9BVkyMPhtg7lOiD8xak1OtPaE2tI+A+fkEoz1JXjib8wohetRfmqm/Cm+XtMij8El0FnW8KRzSlndDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T16:11:34.133550Z"},"content_sha256":"9a565d29ea51d8cc08607741a9ecd6b9c5e565a005459d71a2f857f284b8a613","schema_version":"1.0","event_id":"sha256:9a565d29ea51d8cc08607741a9ecd6b9c5e565a005459d71a2f857f284b8a613"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4UJIG5XJBEVWKVBOVMNT7Q3GRE/bundle.json","state_url":"https://pith.science/pith/4UJIG5XJBEVWKVBOVMNT7Q3GRE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4UJIG5XJBEVWKVBOVMNT7Q3GRE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T16:11:34Z","links":{"resolver":"https://pith.science/pith/4UJIG5XJBEVWKVBOVMNT7Q3GRE","bundle":"https://pith.science/pith/4UJIG5XJBEVWKVBOVMNT7Q3GRE/bundle.json","state":"https://pith.science/pith/4UJIG5XJBEVWKVBOVMNT7Q3GRE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4UJIG5XJBEVWKVBOVMNT7Q3GRE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3V8z8kDCbEGtq6CI0dhiuzSLdxoek5tn9kz4+2XzeD4Uy4Or7WOpsUi8rnyvBtS5o31+ury/tikLSi4r1vN2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T16:11:34.137869Z","bundle_sha256":"8c1b5e8d9ba32f933d00a5e4817b5926c04d239b70c47b7f8e3a8546f9fe21db"}}