{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:G6LZXHRWV62UEYLI2QSB5DEKJM","short_pith_number":"pith:G6LZXHRW","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"},"canonical_sha256":"37979b9e36afb5426168d4241e8c8a4b01c36a6318bef3e14b6912d76d38c82f","source":{"kind":"arxiv","id":"1902.09667","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09667","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09667v1","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09667","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"G6LZXHRWV62U","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"G6LZXHRWV62UEYLI","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"G6LZXHRW","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:G6LZXHRWV62UEYLI2QSB5DEKJM","target":"record","payload":{"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"},"canonical_sha256":"37979b9e36afb5426168d4241e8c8a4b01c36a6318bef3e14b6912d76d38c82f","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"},"source_kind":"arxiv","source_id":"1902.09667","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QeVIt9xE5L56BO1e2ytd0z/UFL+/vG2hgVBGQ+S5ecx6BdeiwW2oizR5bIeYyz5nYM7q2bHXV+6lXy5WFE4lDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:52:11.807560Z"},"content_sha256":"0452174bc28fe231832634495989436514ca4ac7e5384ad32ab42ca1584dfe14","schema_version":"1.0","event_id":"sha256:0452174bc28fe231832634495989436514ca4ac7e5384ad32ab42ca1584dfe14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:G6LZXHRWV62UEYLI2QSB5DEKJM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SwLRPl8HoGVzzljnyu4jMWPkaM5SQBAxFkFJI4VlJUwo5kvsADTWoyIjSWfhhyJFQ38JvGKhxsbfMPZILzTODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:52:11.808193Z"},"content_sha256":"d2e43f9f69840245fef3aad3dd2880db1da4c9206b0f75707735d748feba1e43","schema_version":"1.0","event_id":"sha256:d2e43f9f69840245fef3aad3dd2880db1da4c9206b0f75707735d748feba1e43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/bundle.json","state_url":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/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":"2026-06-04T02:52:11Z","links":{"resolver":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM","bundle":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/bundle.json","state":"https://pith.science/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G6LZXHRWV62UEYLI2QSB5DEKJM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:G6LZXHRWV62UEYLI2QSB5DEKJM","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":"673eace845378d590c754b5695a8a1315e670515b8070cac1abd67364698f70a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-02-25T23:58:38Z","title_canon_sha256":"6905eeec5b7ffce3fc390fc4e457b8b6b9f6fc048a15cf3ac9d71f5e158a1f36"},"schema_version":"1.0","source":{"id":"1902.09667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09667","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09667v1","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09667","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"G6LZXHRWV62U","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"G6LZXHRWV62UEYLI","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"G6LZXHRW","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:d2e43f9f69840245fef3aad3dd2880db1da4c9206b0f75707735d748feba1e43","target":"graph","created_at":"2026-05-17T23:52:35Z","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"},"paper":{"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-","authors_text":"A\\'ecio Santos, Juliana Freire, Kien Pham","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-02-25T23:58:38Z","title":"Bootstrapping Domain-Specific Content Discovery on the Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09667","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":"sha256:0452174bc28fe231832634495989436514ca4ac7e5384ad32ab42ca1584dfe14","target":"record","created_at":"2026-05-17T23:52:35Z","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":"673eace845378d590c754b5695a8a1315e670515b8070cac1abd67364698f70a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-02-25T23:58:38Z","title_canon_sha256":"6905eeec5b7ffce3fc390fc4e457b8b6b9f6fc048a15cf3ac9d71f5e158a1f36"},"schema_version":"1.0","source":{"id":"1902.09667","kind":"arxiv","version":1}},"canonical_sha256":"37979b9e36afb5426168d4241e8c8a4b01c36a6318bef3e14b6912d76d38c82f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37979b9e36afb5426168d4241e8c8a4b01c36a6318bef3e14b6912d76d38c82f","first_computed_at":"2026-05-17T23:52:35.626521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:35.626521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pLsf2r5SIfbq7v7YH5WwkyIvepzI487SeZ3Wx+h6vWKSk2iGWyfgAB+SSE9Am5qaWxqGnQJgrBRyfhYGO6msAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:35.626978Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0452174bc28fe231832634495989436514ca4ac7e5384ad32ab42ca1584dfe14","sha256:d2e43f9f69840245fef3aad3dd2880db1da4c9206b0f75707735d748feba1e43"],"state_sha256":"c6f965e7a7cf96970425845e0fa2f6e8fab67399a9dfd894a637df1de31d26c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P2biVQpNofeB7iM1fTNQ/gGnTAhsBrUH3Rk8UNfc25WCZ+NpuiW01uOLxjVV+v40g0ZoBYgHZMjtrjIl9fAvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T02:52:11.811211Z","bundle_sha256":"a3137dbc195e203c17dcf27c64d72b510ed0c62aa357e15e27c79c74205f99d8"}}