{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BDBD6YNKTLUTR2Y6V7PW2NTO7H","short_pith_number":"pith:BDBD6YNK","schema_version":"1.0","canonical_sha256":"08c23f61aa9ae938eb1eafdf6d366ef9dd48a8011641c25fd183a2ffab93bb52","source":{"kind":"arxiv","id":"2506.01775","version":1},"attestation_state":"computed","paper":{"title":"Developing a Mixed-Methods Pipeline for Community-Oriented Digitization of Kwak'wala Legacy Texts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Daisy Rosenblum, Milind Agarwal","submitted_at":"2025-06-02T15:20:09Z","abstract_excerpt":"Kwak'wala is an Indigenous language spoken in British Columbia, with a rich legacy of published documentation spanning more than a century, and an active community of speakers, teachers, and learners engaged in language revitalization. Over 11 volumes of the earliest texts created during the collaboration between Franz Boas and George Hunt have been scanned but remain unreadable by machines. Complete digitization through optical character recognition has the potential to facilitate transliteration into modern orthographies and the creation of other language technologies. In this paper, we appl"},"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":"2506.01775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T15:20:09Z","cross_cats_sorted":[],"title_canon_sha256":"a9a3d6ba9b50ecce475fa061280cfd0fd625c3bdfb84f545e0ff9d1dd3ae5a94","abstract_canon_sha256":"7f29b1bd740a35048d701e735e948d8ef918ddcd318c36fda6989733834db92d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:19.167764Z","signature_b64":"j+/YnAH9Lu+dyqw620YJGSegKb39K89uMyxJZgG2A1V5ZPU/6fhcsY5bldSP5OnC2gMqF5Zm6nx4DS0ipaY9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08c23f61aa9ae938eb1eafdf6d366ef9dd48a8011641c25fd183a2ffab93bb52","last_reissued_at":"2026-07-05T11:14:19.167272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:19.167272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Developing a Mixed-Methods Pipeline for Community-Oriented Digitization of Kwak'wala Legacy Texts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Daisy Rosenblum, Milind Agarwal","submitted_at":"2025-06-02T15:20:09Z","abstract_excerpt":"Kwak'wala is an Indigenous language spoken in British Columbia, with a rich legacy of published documentation spanning more than a century, and an active community of speakers, teachers, and learners engaged in language revitalization. Over 11 volumes of the earliest texts created during the collaboration between Franz Boas and George Hunt have been scanned but remain unreadable by machines. Complete digitization through optical character recognition has the potential to facilitate transliteration into modern orthographies and the creation of other language technologies. In this paper, we appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01775","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/2506.01775/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":"2506.01775","created_at":"2026-07-05T11:14:19.167342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01775v1","created_at":"2026-07-05T11:14:19.167342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01775","created_at":"2026-07-05T11:14:19.167342+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDBD6YNKTLUT","created_at":"2026-07-05T11:14:19.167342+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDBD6YNKTLUTR2Y6","created_at":"2026-07-05T11:14:19.167342+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDBD6YNK","created_at":"2026-07-05T11:14:19.167342+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/BDBD6YNKTLUTR2Y6V7PW2NTO7H","json":"https://pith.science/pith/BDBD6YNKTLUTR2Y6V7PW2NTO7H.json","graph_json":"https://pith.science/api/pith-number/BDBD6YNKTLUTR2Y6V7PW2NTO7H/graph.json","events_json":"https://pith.science/api/pith-number/BDBD6YNKTLUTR2Y6V7PW2NTO7H/events.json","paper":"https://pith.science/paper/BDBD6YNK"},"agent_actions":{"view_html":"https://pith.science/pith/BDBD6YNKTLUTR2Y6V7PW2NTO7H","download_json":"https://pith.science/pith/BDBD6YNKTLUTR2Y6V7PW2NTO7H.json","view_paper":"https://pith.science/paper/BDBD6YNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01775&json=true","fetch_graph":"https://pith.science/api/pith-number/BDBD6YNKTLUTR2Y6V7PW2NTO7H/graph.json","fetch_events":"https://pith.science/api/pith-number/BDBD6YNKTLUTR2Y6V7PW2NTO7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDBD6YNKTLUTR2Y6V7PW2NTO7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDBD6YNKTLUTR2Y6V7PW2NTO7H/action/storage_attestation","attest_author":"https://pith.science/pith/BDBD6YNKTLUTR2Y6V7PW2NTO7H/action/author_attestation","sign_citation":"https://pith.science/pith/BDBD6YNKTLUTR2Y6V7PW2NTO7H/action/citation_signature","submit_replication":"https://pith.science/pith/BDBD6YNKTLUTR2Y6V7PW2NTO7H/action/replication_record"}},"created_at":"2026-07-05T11:14:19.167342+00:00","updated_at":"2026-07-05T11:14:19.167342+00:00"}