{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M3S3TIBBJY6JT3CNBJSTXXLSA5","short_pith_number":"pith:M3S3TIBB","schema_version":"1.0","canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","source":{"kind":"arxiv","id":"2607.10020","version":1},"attestation_state":"computed","paper":{"title":"Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lars Henry Berge Olsen, Mark Anderson, Martin Jullum, Pierre Lison","submitted_at":"2026-07-10T22:46:11Z","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 "},"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":"2607.10020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca1fad18a95c18b8a5bd59afa608234568313aed576389e140a596b6c9524637","abstract_canon_sha256":"59924e3b6bcb1909294d104aa76357788eb74af0f845594e52ea09c7d830cb32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:47.931036Z","signature_b64":"sUWeW9eS0RtRDmPWLxWsKZ8/w7k6Rx96iJsvndGkBWRYmUsF+7jeWRCh+l8q98HV5HiMPcb4Ck66wQAPVcJdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","last_reissued_at":"2026-07-14T00:18:47.930255Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:47.930255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lars Henry Berge Olsen, Mark Anderson, Martin Jullum, Pierre Lison","submitted_at":"2026-07-10T22:46:11Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10020","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/2607.10020/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":"2607.10020","created_at":"2026-07-14T00:18:47.930677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10020v1","created_at":"2026-07-14T00:18:47.930677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10020","created_at":"2026-07-14T00:18:47.930677+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3S3TIBBJY6J","created_at":"2026-07-14T00:18:47.930677+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3S3TIBBJY6JT3CN","created_at":"2026-07-14T00:18:47.930677+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3S3TIBB","created_at":"2026-07-14T00:18:47.930677+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/M3S3TIBBJY6JT3CNBJSTXXLSA5","json":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5.json","graph_json":"https://pith.science/api/pith-number/M3S3TIBBJY6JT3CNBJSTXXLSA5/graph.json","events_json":"https://pith.science/api/pith-number/M3S3TIBBJY6JT3CNBJSTXXLSA5/events.json","paper":"https://pith.science/paper/M3S3TIBB"},"agent_actions":{"view_html":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5","download_json":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5.json","view_paper":"https://pith.science/paper/M3S3TIBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10020&json=true","fetch_graph":"https://pith.science/api/pith-number/M3S3TIBBJY6JT3CNBJSTXXLSA5/graph.json","fetch_events":"https://pith.science/api/pith-number/M3S3TIBBJY6JT3CNBJSTXXLSA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/action/storage_attestation","attest_author":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/action/author_attestation","sign_citation":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/action/citation_signature","submit_replication":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/action/replication_record"}},"created_at":"2026-07-14T00:18:47.930677+00:00","updated_at":"2026-07-14T00:18:47.930677+00:00"}