{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L3LVS4YNNAPKGBX6MUNC434ADF","short_pith_number":"pith:L3LVS4YN","schema_version":"1.0","canonical_sha256":"5ed759730d681ea306fe651a2e6f80196754a3f76885829156927d86c75549aa","source":{"kind":"arxiv","id":"2407.20595","version":4},"attestation_state":"computed","paper":{"title":"HALvest-Contrastive: Retrieval-Like Authorship Attribution with Patch-Level Late Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Florian Cafiero, Francis Kulumba, Guillaume Vimont, Laurent Romary, Wissam Antoun","submitted_at":"2024-07-30T07:14:04Z","abstract_excerpt":"Deciding whether two pieces of text share an author is made difficult by topical confound: two writers covering the same topic often look more alike than one writer covering two topics. We tackle this with HALvest, a 17-billion-token multilingual corpus of open-access scholarly papers, and its English contrastive derivative HALvest-Contrastive, in which same-author passages are drawn from distinct papers within a field to minimize topical overlap. We also revisit how documents are compared. Authorship systems traditionally compress each document into a single vector, we keep a sequence of vect"},"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":"2407.20595","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2024-07-30T07:14:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0edec4b141b1888ca4fa0cfcc75f08a228df7f670c581bc263a1c1128f466e82","abstract_canon_sha256":"aaabcdd6f558109f0b2d17f3d1b2d127ccbcaa1fb19c90566a3a6349dbbde13e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:04:49.817950Z","signature_b64":"POV5HZrShtQoiOH4nV/2QKL9FRcIrnA5FpP9THA/sF6dWSCEyEtC688vL8ve5u1YB1Y4OKKd0vg0Xtzsqc9vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ed759730d681ea306fe651a2e6f80196754a3f76885829156927d86c75549aa","last_reissued_at":"2026-05-20T01:04:49.817011Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:04:49.817011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HALvest-Contrastive: Retrieval-Like Authorship Attribution with Patch-Level Late Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Florian Cafiero, Francis Kulumba, Guillaume Vimont, Laurent Romary, Wissam Antoun","submitted_at":"2024-07-30T07:14:04Z","abstract_excerpt":"Deciding whether two pieces of text share an author is made difficult by topical confound: two writers covering the same topic often look more alike than one writer covering two topics. We tackle this with HALvest, a 17-billion-token multilingual corpus of open-access scholarly papers, and its English contrastive derivative HALvest-Contrastive, in which same-author passages are drawn from distinct papers within a field to minimize topical overlap. We also revisit how documents are compared. Authorship systems traditionally compress each document into a single vector, we keep a sequence of vect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20595","kind":"arxiv","version":4},"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/2407.20595/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":"2407.20595","created_at":"2026-05-20T01:04:49.817134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.20595v4","created_at":"2026-05-20T01:04:49.817134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20595","created_at":"2026-05-20T01:04:49.817134+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3LVS4YNNAPK","created_at":"2026-05-20T01:04:49.817134+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3LVS4YNNAPKGBX6","created_at":"2026-05-20T01:04:49.817134+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3LVS4YN","created_at":"2026-05-20T01:04:49.817134+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/L3LVS4YNNAPKGBX6MUNC434ADF","json":"https://pith.science/pith/L3LVS4YNNAPKGBX6MUNC434ADF.json","graph_json":"https://pith.science/api/pith-number/L3LVS4YNNAPKGBX6MUNC434ADF/graph.json","events_json":"https://pith.science/api/pith-number/L3LVS4YNNAPKGBX6MUNC434ADF/events.json","paper":"https://pith.science/paper/L3LVS4YN"},"agent_actions":{"view_html":"https://pith.science/pith/L3LVS4YNNAPKGBX6MUNC434ADF","download_json":"https://pith.science/pith/L3LVS4YNNAPKGBX6MUNC434ADF.json","view_paper":"https://pith.science/paper/L3LVS4YN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.20595&json=true","fetch_graph":"https://pith.science/api/pith-number/L3LVS4YNNAPKGBX6MUNC434ADF/graph.json","fetch_events":"https://pith.science/api/pith-number/L3LVS4YNNAPKGBX6MUNC434ADF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3LVS4YNNAPKGBX6MUNC434ADF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3LVS4YNNAPKGBX6MUNC434ADF/action/storage_attestation","attest_author":"https://pith.science/pith/L3LVS4YNNAPKGBX6MUNC434ADF/action/author_attestation","sign_citation":"https://pith.science/pith/L3LVS4YNNAPKGBX6MUNC434ADF/action/citation_signature","submit_replication":"https://pith.science/pith/L3LVS4YNNAPKGBX6MUNC434ADF/action/replication_record"}},"created_at":"2026-05-20T01:04:49.817134+00:00","updated_at":"2026-05-20T01:04:49.817134+00:00"}