{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KEMREUDNIXAWBZLZSIQJGB4YQW","short_pith_number":"pith:KEMREUDN","schema_version":"1.0","canonical_sha256":"511912506d45c160e579922093079885989e00ce265d70c3fd2af6152b464959","source":{"kind":"arxiv","id":"2209.06869","version":2},"attestation_state":"computed","paper":{"title":"On the State of the Art in Authorship Attribution and Authorship Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Jacob Tyo, Zachary C. Lipton","submitted_at":"2022-09-14T18:32:26Z","abstract_excerpt":"Despite decades of research on authorship attribution (AA) and authorship verification (AV), inconsistent dataset splits/filtering and mismatched evaluation methods make it difficult to assess the state of the art. In this paper, we present a survey of the fields, resolve points of confusion, introduce Valla that standardizes and benchmarks AA/AV datasets and metrics, provide a large-scale empirical evaluation, and provide apples-to-apples comparisons between existing methods. We evaluate eight promising methods on fifteen datasets (including distribution-shifted challenge sets) and introduce "},"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":"2209.06869","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-14T18:32:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7c4dc9d725d07104fe0ae1817f4d57b7a9945ca4224631c822ffd051317446d8","abstract_canon_sha256":"84a394fec6bf1554c0baa20a75222e9c38294ccbeab2c274eb2de06d8289226a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:39.385088Z","signature_b64":"JD0d3X/SLi6TdLyK/hEdPhVmjK9gmNmabd4HKwk91wYDMbuwVvFVKcvreCRPwLjtdlxfuU6wbdVrkTAWvYCVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"511912506d45c160e579922093079885989e00ce265d70c3fd2af6152b464959","last_reissued_at":"2026-07-05T05:03:39.384674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:39.384674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the State of the Art in Authorship Attribution and Authorship Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Jacob Tyo, Zachary C. Lipton","submitted_at":"2022-09-14T18:32:26Z","abstract_excerpt":"Despite decades of research on authorship attribution (AA) and authorship verification (AV), inconsistent dataset splits/filtering and mismatched evaluation methods make it difficult to assess the state of the art. In this paper, we present a survey of the fields, resolve points of confusion, introduce Valla that standardizes and benchmarks AA/AV datasets and metrics, provide a large-scale empirical evaluation, and provide apples-to-apples comparisons between existing methods. We evaluate eight promising methods on fifteen datasets (including distribution-shifted challenge sets) and introduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06869","kind":"arxiv","version":2},"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/2209.06869/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":"2209.06869","created_at":"2026-07-05T05:03:39.384732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06869v2","created_at":"2026-07-05T05:03:39.384732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06869","created_at":"2026-07-05T05:03:39.384732+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEMREUDNIXAW","created_at":"2026-07-05T05:03:39.384732+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEMREUDNIXAWBZLZ","created_at":"2026-07-05T05:03:39.384732+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEMREUDN","created_at":"2026-07-05T05:03:39.384732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06755","citing_title":"PromptPrint: Behavioral Biometrics Through Natural Language Prompting in LLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05716","citing_title":"Interpreting Style Representations via Style-Eliciting Prompts","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18955","citing_title":"Assessing Capabilities of Large Language Models in Social Media Analytics: A Multi-task Quest","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW","json":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW.json","graph_json":"https://pith.science/api/pith-number/KEMREUDNIXAWBZLZSIQJGB4YQW/graph.json","events_json":"https://pith.science/api/pith-number/KEMREUDNIXAWBZLZSIQJGB4YQW/events.json","paper":"https://pith.science/paper/KEMREUDN"},"agent_actions":{"view_html":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW","download_json":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW.json","view_paper":"https://pith.science/paper/KEMREUDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06869&json=true","fetch_graph":"https://pith.science/api/pith-number/KEMREUDNIXAWBZLZSIQJGB4YQW/graph.json","fetch_events":"https://pith.science/api/pith-number/KEMREUDNIXAWBZLZSIQJGB4YQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW/action/storage_attestation","attest_author":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW/action/author_attestation","sign_citation":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW/action/citation_signature","submit_replication":"https://pith.science/pith/KEMREUDNIXAWBZLZSIQJGB4YQW/action/replication_record"}},"created_at":"2026-07-05T05:03:39.384732+00:00","updated_at":"2026-07-05T05:03:39.384732+00:00"}