{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2000:2GW4ONQXRUXFNL6JN4PWC7K2SP","short_pith_number":"pith:2GW4ONQX","canonical_record":{"source":{"id":"cs/0003043","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.DB","submitted_at":"2000-03-09T04:01:22Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"8340d243b6f5b4d9c17f170eb0ab40ee996e991eb9b340e68900d20177e9abdd","abstract_canon_sha256":"998cab61c7af655dc28c22ab2e2a9df82d71bdf8a4ed0e36b25b09dce185fcc5"},"schema_version":"1.0"},"canonical_sha256":"d1adc736178d2e56afc96f1f617d5a93ddeae4d9446a5d6f6d90ca281d98cc6e","source":{"kind":"arxiv","id":"cs/0003043","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0003043","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0003043v1","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0003043","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"2GW4ONQXRUXF","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"2GW4ONQXRUXFNL6J","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"2GW4ONQX","created_at":"2026-07-04T14:24:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2000:2GW4ONQXRUXFNL6JN4PWC7K2SP","target":"record","payload":{"canonical_record":{"source":{"id":"cs/0003043","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.DB","submitted_at":"2000-03-09T04:01:22Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"8340d243b6f5b4d9c17f170eb0ab40ee996e991eb9b340e68900d20177e9abdd","abstract_canon_sha256":"998cab61c7af655dc28c22ab2e2a9df82d71bdf8a4ed0e36b25b09dce185fcc5"},"schema_version":"1.0"},"canonical_sha256":"d1adc736178d2e56afc96f1f617d5a93ddeae4d9446a5d6f6d90ca281d98cc6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:24:01.295059Z","signature_b64":"XWELwGdlUKj1iMCEmDJ+9obSdBe3TyVGNgSPOmNRWKY5yqiAjEF/Z06O+Bi26uGicv6pEqQ2xrHSY/TfXSbmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1adc736178d2e56afc96f1f617d5a93ddeae4d9446a5d6f6d90ca281d98cc6e","last_reissued_at":"2026-07-04T14:24:01.294684Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:24:01.294684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"cs/0003043","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":"2026-07-04T14:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G9JbzbFwHVMhQCp5ogxcGxls5O/l68UjM+/93sBrKs4qNobqYRzOtLk4RfzQs7vU2A4IKSAMWuY4+dIFlNuhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:42:26.155226Z"},"content_sha256":"817487657a66d2d204578448c9446fc7d5a4c9fa5feb17fd256189c096867678","schema_version":"1.0","event_id":"sha256:817487657a66d2d204578448c9446fc7d5a4c9fa5feb17fd256189c096867678"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2000:2GW4ONQXRUXFNL6JN4PWC7K2SP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Classification of Text Databases through Query Probing","license":"","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Luis Gravano, Mehran Sahami, Panagiotis Ipeirotis","submitted_at":"2000-03-09T04:01:22Z","abstract_excerpt":"Many text databases on the web are \"hidden\" behind search interfaces, and their documents are only accessible through querying. Search engines typically ignore the contents of such search-only databases. Recently, Yahoo-like directories have started to manually organize these databases into categories that users can browse to find these valuable resources. We propose a novel strategy to automate the classification of search-only text databases. Our technique starts by training a rule-based document classifier, and then uses the classifier's rules to generate probing queries. The queries are se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0003043","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/cs/0003043/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":"2026-07-04T14:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jhOCIDqeCq8MomLGq2070vcKr1D472yTmOOtyUW2/opSBE3E1FU/JiKw4Ou8uMCm78LyI6ptTIvJbUbmdrLoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:42:26.155618Z"},"content_sha256":"195652e5b47464d034a533ef1197f5b4693af322a268bc6a225677ec1504f050","schema_version":"1.0","event_id":"sha256:195652e5b47464d034a533ef1197f5b4693af322a268bc6a225677ec1504f050"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2GW4ONQXRUXFNL6JN4PWC7K2SP/bundle.json","state_url":"https://pith.science/pith/2GW4ONQXRUXFNL6JN4PWC7K2SP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2GW4ONQXRUXFNL6JN4PWC7K2SP/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":"2026-07-07T15:42:26Z","links":{"resolver":"https://pith.science/pith/2GW4ONQXRUXFNL6JN4PWC7K2SP","bundle":"https://pith.science/pith/2GW4ONQXRUXFNL6JN4PWC7K2SP/bundle.json","state":"https://pith.science/pith/2GW4ONQXRUXFNL6JN4PWC7K2SP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2GW4ONQXRUXFNL6JN4PWC7K2SP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2000:2GW4ONQXRUXFNL6JN4PWC7K2SP","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":"998cab61c7af655dc28c22ab2e2a9df82d71bdf8a4ed0e36b25b09dce185fcc5","cross_cats_sorted":["cs.IR"],"license":"","primary_cat":"cs.DB","submitted_at":"2000-03-09T04:01:22Z","title_canon_sha256":"8340d243b6f5b4d9c17f170eb0ab40ee996e991eb9b340e68900d20177e9abdd"},"schema_version":"1.0","source":{"id":"cs/0003043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0003043","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0003043v1","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0003043","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"2GW4ONQXRUXF","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"2GW4ONQXRUXFNL6J","created_at":"2026-07-04T14:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"2GW4ONQX","created_at":"2026-07-04T14:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:195652e5b47464d034a533ef1197f5b4693af322a268bc6a225677ec1504f050","target":"graph","created_at":"2026-07-04T14:24:01Z","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/cs/0003043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many text databases on the web are \"hidden\" behind search interfaces, and their documents are only accessible through querying. Search engines typically ignore the contents of such search-only databases. Recently, Yahoo-like directories have started to manually organize these databases into categories that users can browse to find these valuable resources. We propose a novel strategy to automate the classification of search-only text databases. Our technique starts by training a rule-based document classifier, and then uses the classifier's rules to generate probing queries. The queries are se","authors_text":"Luis Gravano, Mehran Sahami, Panagiotis Ipeirotis","cross_cats":["cs.IR"],"headline":"","license":"","primary_cat":"cs.DB","submitted_at":"2000-03-09T04:01:22Z","title":"Automatic Classification of Text Databases through Query Probing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0003043","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":"sha256:817487657a66d2d204578448c9446fc7d5a4c9fa5feb17fd256189c096867678","target":"record","created_at":"2026-07-04T14:24:01Z","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":"998cab61c7af655dc28c22ab2e2a9df82d71bdf8a4ed0e36b25b09dce185fcc5","cross_cats_sorted":["cs.IR"],"license":"","primary_cat":"cs.DB","submitted_at":"2000-03-09T04:01:22Z","title_canon_sha256":"8340d243b6f5b4d9c17f170eb0ab40ee996e991eb9b340e68900d20177e9abdd"},"schema_version":"1.0","source":{"id":"cs/0003043","kind":"arxiv","version":1}},"canonical_sha256":"d1adc736178d2e56afc96f1f617d5a93ddeae4d9446a5d6f6d90ca281d98cc6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1adc736178d2e56afc96f1f617d5a93ddeae4d9446a5d6f6d90ca281d98cc6e","first_computed_at":"2026-07-04T14:24:01.294684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T14:24:01.294684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XWELwGdlUKj1iMCEmDJ+9obSdBe3TyVGNgSPOmNRWKY5yqiAjEF/Z06O+Bi26uGicv6pEqQ2xrHSY/TfXSbmAA==","signature_status":"signed_v1","signed_at":"2026-07-04T14:24:01.295059Z","signed_message":"canonical_sha256_bytes"},"source_id":"cs/0003043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:817487657a66d2d204578448c9446fc7d5a4c9fa5feb17fd256189c096867678","sha256:195652e5b47464d034a533ef1197f5b4693af322a268bc6a225677ec1504f050"],"state_sha256":"4de4f6c793a3950c4574048deff6923a6e3ece727f75d0dd762fbdf2ea1590e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86dt13bhmPvPi4HTufCYEeZ9l7e/ny5bs1RsknWYpcj5f5xypIMdtZpoLBdQDIcasEpybcXybFOlqyJkcfQVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:42:26.157582Z","bundle_sha256":"01b58f84e24589515e3504e981ac5b4d44779bb6ebec21ae5eeb5f5b400b04c7"}}