{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2000:RSOHIQPRYSRHRONSJ2WZEL2FGK","short_pith_number":"pith:RSOHIQPR","schema_version":"1.0","canonical_sha256":"8c9c7441f1c4a278b9b24ead922f45328efb80d5171ec3569ba3ad5ed5273241","source":{"kind":"arxiv","id":"cs/0006013","version":1},"attestation_state":"computed","paper":{"title":"An evaluation of Naive Bayesian anti-spam filtering","license":"","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Constantine D. Spyropoulos, George Paliouras, Ion Androutsopoulos, John Koutsias, Konstantinos V. Chandrinos","submitted_at":"2000-06-07T11:10:50Z","abstract_excerpt":"It has recently been argued that a Naive Bayesian classifier can be used to filter unsolicited bulk e-mail (\"spam\"). We conduct a thorough evaluation of this proposal on a corpus that we make publicly available, contributing towards standard benchmarks. At the same time we investigate the effect of attribute-set size, training-corpus size, lemmatization, and stop-lists on the filter's performance, issues that had not been previously explored. After introducing appropriate cost-sensitive evaluation measures, we reach the conclusion that additional safety nets are needed for the Naive Bayesian a"},"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":"cs/0006013","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CL","submitted_at":"2000-06-07T11:10:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b23746a838485ba546bd84db9315e586b6df0507af8b87c0f350649d71fa708","abstract_canon_sha256":"431ee1db310dacdfc06f6a7c5a94e2c5dd9994e849cc227dc1698b777493c503"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:51:19.138842Z","signature_b64":"IH4O94jVNa6LD1E9PefFpA5gacfnlst9RHosq32qNRN8Wep+NYTsq8XEHRlVwM1Jzu/RTuwbee1ACtXiU/a2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c9c7441f1c4a278b9b24ead922f45328efb80d5171ec3569ba3ad5ed5273241","last_reissued_at":"2026-07-04T15:51:19.138256Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:51:19.138256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An evaluation of Naive Bayesian anti-spam filtering","license":"","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Constantine D. Spyropoulos, George Paliouras, Ion Androutsopoulos, John Koutsias, Konstantinos V. Chandrinos","submitted_at":"2000-06-07T11:10:50Z","abstract_excerpt":"It has recently been argued that a Naive Bayesian classifier can be used to filter unsolicited bulk e-mail (\"spam\"). We conduct a thorough evaluation of this proposal on a corpus that we make publicly available, contributing towards standard benchmarks. At the same time we investigate the effect of attribute-set size, training-corpus size, lemmatization, and stop-lists on the filter's performance, issues that had not been previously explored. After introducing appropriate cost-sensitive evaluation measures, we reach the conclusion that additional safety nets are needed for the Naive Bayesian a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0006013","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/0006013/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"cs/0006013","created_at":"2026-07-04T15:51:19.138370+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0006013v1","created_at":"2026-07-04T15:51:19.138370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0006013","created_at":"2026-07-04T15:51:19.138370+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSOHIQPRYSRH","created_at":"2026-07-04T15:51:19.138370+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSOHIQPRYSRHRONS","created_at":"2026-07-04T15:51:19.138370+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSOHIQPR","created_at":"2026-07-04T15:51:19.138370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.00034","citing_title":"Improving Phishing Email Detection Performance of Small Large Language Models","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK","json":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK.json","graph_json":"https://pith.science/api/pith-number/RSOHIQPRYSRHRONSJ2WZEL2FGK/graph.json","events_json":"https://pith.science/api/pith-number/RSOHIQPRYSRHRONSJ2WZEL2FGK/events.json","paper":"https://pith.science/paper/RSOHIQPR"},"agent_actions":{"view_html":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK","download_json":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK.json","view_paper":"https://pith.science/paper/RSOHIQPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0006013&json=true","fetch_graph":"https://pith.science/api/pith-number/RSOHIQPRYSRHRONSJ2WZEL2FGK/graph.json","fetch_events":"https://pith.science/api/pith-number/RSOHIQPRYSRHRONSJ2WZEL2FGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK/action/storage_attestation","attest_author":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK/action/author_attestation","sign_citation":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK/action/citation_signature","submit_replication":"https://pith.science/pith/RSOHIQPRYSRHRONSJ2WZEL2FGK/action/replication_record"}},"created_at":"2026-07-04T15:51:19.138370+00:00","updated_at":"2026-07-04T15:51:19.138370+00:00"}