{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G6LZXHRWV62UEYLI2QSB5DEKJM","short_pith_number":"pith:G6LZXHRW","schema_version":"1.0","canonical_sha256":"37979b9e36afb5426168d4241e8c8a4b01c36a6318bef3e14b6912d76d38c82f","source":{"kind":"arxiv","id":"1902.09667","version":1},"attestation_state":"computed","paper":{"title":"Bootstrapping Domain-Specific Content Discovery on the Web","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"A\\'ecio Santos, Juliana Freire, Kien Pham","submitted_at":"2019-02-25T23:58:38Z","abstract_excerpt":"The ability to continuously discover domain-specific content from the Web is critical for many applications. While focused crawling strategies have been shown to be effective for discovery, configuring a focused crawler is difficult and time-consuming. Given a domain of interest $D$, subject-matter experts (SMEs) must search for relevant websites and collect a set of representative Web pages to serve as training examples for creating a classifier that recognizes pages in $D$, as well as a set of pages to seed the crawl. In this paper, we propose DISCO, an approach designed to bootstrap domain-"},"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":"1902.09667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-02-25T23:58:38Z","cross_cats_sorted":[],"title_canon_sha256":"6905eeec5b7ffce3fc390fc4e457b8b6b9f6fc048a15cf3ac9d71f5e158a1f36","abstract_canon_sha256":"673eace845378d590c754b5695a8a1315e670515b8070cac1abd67364698f70a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:35.626978Z","signature_b64":"pLsf2r5SIfbq7v7YH5WwkyIvepzI487SeZ3Wx+h6vWKSk2iGWyfgAB+SSE9Am5qaWxqGnQJgrBRyfhYGO6msAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37979b9e36afb5426168d4241e8c8a4b01c36a6318bef3e14b6912d76d38c82f","last_reissued_at":"2026-05-17T23:52:35.626521Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:35.626521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapping Domain-Specific Content Discovery on the Web","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"A\\'ecio Santos, Juliana Freire, Kien Pham","submitted_at":"2019-02-25T23:58:38Z","abstract_excerpt":"The ability to continuously discover domain-specific content from the Web is critical for many applications. While focused crawling strategies have been shown to be effective for discovery, configuring a focused crawler is difficult and time-consuming. Given a domain of interest $D$, subject-matter experts (SMEs) must search for relevant websites and collect a set of representative Web pages to serve as training examples for creating a classifier that recognizes pages in $D$, as well as a set of pages to seed the crawl. In this paper, we propose DISCO, an approach designed to bootstrap domain-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09667","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":""},"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":"1902.09667","created_at":"2026-05-17T23:52:35.626591+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.09667v1","created_at":"2026-05-17T23:52:35.626591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09667","created_at":"2026-05-17T23:52:35.626591+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6LZXHRWV62U","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6LZXHRWV62UEYLI","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6LZXHRW","created_at":"2026-05-18T12:33:18.533446+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/G6LZXHRWV62UEYLI2QSB5DEKJM","json":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM.json","graph_json":"https://pith.science/api/pith-number/G6LZXHRWV62UEYLI2QSB5DEKJM/graph.json","events_json":"https://pith.science/api/pith-number/G6LZXHRWV62UEYLI2QSB5DEKJM/events.json","paper":"https://pith.science/paper/G6LZXHRW"},"agent_actions":{"view_html":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM","download_json":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM.json","view_paper":"https://pith.science/paper/G6LZXHRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.09667&json=true","fetch_graph":"https://pith.science/api/pith-number/G6LZXHRWV62UEYLI2QSB5DEKJM/graph.json","fetch_events":"https://pith.science/api/pith-number/G6LZXHRWV62UEYLI2QSB5DEKJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/action/storage_attestation","attest_author":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/action/author_attestation","sign_citation":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/action/citation_signature","submit_replication":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/action/replication_record"}},"created_at":"2026-05-17T23:52:35.626591+00:00","updated_at":"2026-05-17T23:52:35.626591+00:00"}