{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L3LVS4YNNAPKGBX6MUNC434ADF","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":"aaabcdd6f558109f0b2d17f3d1b2d127ccbcaa1fb19c90566a3a6349dbbde13e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2024-07-30T07:14:04Z","title_canon_sha256":"0edec4b141b1888ca4fa0cfcc75f08a228df7f670c581bc263a1c1128f466e82"},"schema_version":"1.0","source":{"id":"2407.20595","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20595","created_at":"2026-05-20T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20595v4","created_at":"2026-05-20T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20595","created_at":"2026-05-20T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"L3LVS4YNNAPK","created_at":"2026-05-20T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"L3LVS4YNNAPKGBX6","created_at":"2026-05-20T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"L3LVS4YN","created_at":"2026-05-20T01:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:d657de456c088a6e3506e7de68ef724912bceabf9b32c9f8c493c4b5c0a2f861","target":"graph","created_at":"2026-05-20T01:04:49Z","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/2407.20595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Florian Cafiero, Francis Kulumba, Guillaume Vimont, Laurent Romary, Wissam Antoun","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2024-07-30T07:14:04Z","title":"HALvest-Contrastive: Retrieval-Like Authorship Attribution with Patch-Level Late Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20595","kind":"arxiv","version":4},"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:ceb7307848b0a063a44bead8c66ceab4192cf005396702dd82c99a4aa7195a86","target":"record","created_at":"2026-05-20T01:04:49Z","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":"aaabcdd6f558109f0b2d17f3d1b2d127ccbcaa1fb19c90566a3a6349dbbde13e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2024-07-30T07:14:04Z","title_canon_sha256":"0edec4b141b1888ca4fa0cfcc75f08a228df7f670c581bc263a1c1128f466e82"},"schema_version":"1.0","source":{"id":"2407.20595","kind":"arxiv","version":4}},"canonical_sha256":"5ed759730d681ea306fe651a2e6f80196754a3f76885829156927d86c75549aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ed759730d681ea306fe651a2e6f80196754a3f76885829156927d86c75549aa","first_computed_at":"2026-05-20T01:04:49.817011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:04:49.817011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"POV5HZrShtQoiOH4nV/2QKL9FRcIrnA5FpP9THA/sF6dWSCEyEtC688vL8ve5u1YB1Y4OKKd0vg0Xtzsqc9vAw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:04:49.817950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20595","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ceb7307848b0a063a44bead8c66ceab4192cf005396702dd82c99a4aa7195a86","sha256:d657de456c088a6e3506e7de68ef724912bceabf9b32c9f8c493c4b5c0a2f861"],"state_sha256":"9d8ca0b1c005f8495552a14acda32ccf7c1b70a60e82c576e9045b76e24d9e9d"}