{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:NASNPCFFV36ZKE47N23BSVTW55","short_pith_number":"pith:NASNPCFF","schema_version":"1.0","canonical_sha256":"6824d788a5aefd95139f6eb6195676ef67ac35c85b2d29ccd3c8cb527a42fa05","source":{"kind":"arxiv","id":"1208.0075","version":1},"attestation_state":"computed","paper":{"title":"Optimal Algorithms for Crawling a Hidden Database in the Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Cheng Sheng, Nan Zhang, Xin Jin, Yufei Tao","submitted_at":"2012-08-01T03:43:52Z","abstract_excerpt":"A hidden database refers to a dataset that an organization makes accessible on the web by allowing users to issue queries through a search interface. In other words, data acquisition from such a source is not by following static hyper-links. Instead, data are obtained by querying the interface, and reading the result page dynamically generated. This, with other facts such as the interface may answer a query only partially, has prevented hidden databases from being crawled effectively by existing search engines. This paper remedies the problem by giving algorithms to extract all the tuples from"},"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":"1208.0075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-08-01T03:43:52Z","cross_cats_sorted":[],"title_canon_sha256":"b8fa5a027523f0eea6b584622f9994fea15fc277fb75f1f4424f914a66675c17","abstract_canon_sha256":"7cb551ffbb3e0f97e81fb3c767f018c1329f6c2b521b9ee1c39d74543edd9b97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:49:45.087856Z","signature_b64":"zox1O+MV7FVHPq9mdAqOQLCxdUER/jvRYKP59hklaBtK+6vAT8jOYjKjakSFlRd8L9d1c+wScVeFueoKn/c+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6824d788a5aefd95139f6eb6195676ef67ac35c85b2d29ccd3c8cb527a42fa05","last_reissued_at":"2026-05-18T03:49:45.087115Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:49:45.087115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Algorithms for Crawling a Hidden Database in the Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Cheng Sheng, Nan Zhang, Xin Jin, Yufei Tao","submitted_at":"2012-08-01T03:43:52Z","abstract_excerpt":"A hidden database refers to a dataset that an organization makes accessible on the web by allowing users to issue queries through a search interface. In other words, data acquisition from such a source is not by following static hyper-links. Instead, data are obtained by querying the interface, and reading the result page dynamically generated. This, with other facts such as the interface may answer a query only partially, has prevented hidden databases from being crawled effectively by existing search engines. This paper remedies the problem by giving algorithms to extract all the tuples from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.0075","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":"1208.0075","created_at":"2026-05-18T03:49:45.087255+00:00"},{"alias_kind":"arxiv_version","alias_value":"1208.0075v1","created_at":"2026-05-18T03:49:45.087255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.0075","created_at":"2026-05-18T03:49:45.087255+00:00"},{"alias_kind":"pith_short_12","alias_value":"NASNPCFFV36Z","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_16","alias_value":"NASNPCFFV36ZKE47","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_8","alias_value":"NASNPCFF","created_at":"2026-05-18T12:27:16.716162+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/NASNPCFFV36ZKE47N23BSVTW55","json":"https://pith.science/pith/NASNPCFFV36ZKE47N23BSVTW55.json","graph_json":"https://pith.science/api/pith-number/NASNPCFFV36ZKE47N23BSVTW55/graph.json","events_json":"https://pith.science/api/pith-number/NASNPCFFV36ZKE47N23BSVTW55/events.json","paper":"https://pith.science/paper/NASNPCFF"},"agent_actions":{"view_html":"https://pith.science/pith/NASNPCFFV36ZKE47N23BSVTW55","download_json":"https://pith.science/pith/NASNPCFFV36ZKE47N23BSVTW55.json","view_paper":"https://pith.science/paper/NASNPCFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1208.0075&json=true","fetch_graph":"https://pith.science/api/pith-number/NASNPCFFV36ZKE47N23BSVTW55/graph.json","fetch_events":"https://pith.science/api/pith-number/NASNPCFFV36ZKE47N23BSVTW55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NASNPCFFV36ZKE47N23BSVTW55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NASNPCFFV36ZKE47N23BSVTW55/action/storage_attestation","attest_author":"https://pith.science/pith/NASNPCFFV36ZKE47N23BSVTW55/action/author_attestation","sign_citation":"https://pith.science/pith/NASNPCFFV36ZKE47N23BSVTW55/action/citation_signature","submit_replication":"https://pith.science/pith/NASNPCFFV36ZKE47N23BSVTW55/action/replication_record"}},"created_at":"2026-05-18T03:49:45.087255+00:00","updated_at":"2026-05-18T03:49:45.087255+00:00"}