{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M3S3TIBBJY6JT3CNBJSTXXLSA5","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"59924e3b6bcb1909294d104aa76357788eb74af0f845594e52ea09c7d830cb32","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","title_canon_sha256":"ca1fad18a95c18b8a5bd59afa608234568313aed576389e140a596b6c9524637"},"schema_version":"1.0","source":{"id":"2607.10020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10020","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10020v1","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10020","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"M3S3TIBBJY6J","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"M3S3TIBBJY6JT3CN","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"M3S3TIBB","created_at":"2026-07-14T00:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:50b5c39684796619e750720b63b557638fdec9008062587d80f71da0590858fb","target":"graph","created_at":"2026-07-14T00:18:47Z","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/2607.10020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present FindMyText, an open-source Python package designed to efficiently assess whether a given text appears, in part or in full, within a text corpus. The tool builds on prior techniques for document fingerprinting, but extends them with a novel mechanism to explicitly capture sequences of matching fingerprints. By identifying such chains, the tool can more reliably detect near-verbatim copies of a given text rather than mere textual similarities. This makes FindMyText particularly suited for verifying the presence of copyrighted material in a corpus. Leveraging a distributed, disk-based ","authors_text":"Lars Henry Berge Olsen, Mark Anderson, Martin Jullum, Pierre Lison","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","title":"Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10020","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:b7da124bd229572d536f0ecec0ebf206b40e8cb07e4a873e288b54315c29c96a","target":"record","created_at":"2026-07-14T00:18:47Z","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":"59924e3b6bcb1909294d104aa76357788eb74af0f845594e52ea09c7d830cb32","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","title_canon_sha256":"ca1fad18a95c18b8a5bd59afa608234568313aed576389e140a596b6c9524637"},"schema_version":"1.0","source":{"id":"2607.10020","kind":"arxiv","version":1}},"canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","first_computed_at":"2026-07-14T00:18:47.930255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:47.930255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sUWeW9eS0RtRDmPWLxWsKZ8/w7k6Rx96iJsvndGkBWRYmUsF+7jeWRCh+l8q98HV5HiMPcb4Ck66wQAPVcJdDg==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:47.931036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10020","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:8ee4e88f39df952e043c5af73abbf5123d5adc87790ffa6a59e347cadda11b40","sha256:a0d3ae142430c5082b301c2490b17838e636905b7fdcd7d25ac948c95c8bcc07"]}],"invalid_events":[],"applied_event_ids":["sha256:b7da124bd229572d536f0ecec0ebf206b40e8cb07e4a873e288b54315c29c96a","sha256:50b5c39684796619e750720b63b557638fdec9008062587d80f71da0590858fb"],"state_sha256":"600ef788eb5257c33d8e4aa00e2759c7b8d2150bfb7185f00ffab0f64ec0b283"}