{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A7O7LSONX265K5LJRPT3SCTG7Q","short_pith_number":"pith:A7O7LSON","schema_version":"1.0","canonical_sha256":"07ddf5c9cdbebdd575698be7b90a66fc1a1a9746effc2ef6ec47690bb84cd495","source":{"kind":"arxiv","id":"2606.28867","version":1},"attestation_state":"computed","paper":{"title":"Open but Incompatible: A License Compatibility Analysis of Corpora for Low-Resource African Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ernst van Gassen","submitted_at":"2026-06-27T11:16:12Z","abstract_excerpt":"Creative Commons licenses dominate African NLP corpus releases, but their compatibility rules are rarely applied. CC-BY-SA and CC-BY-NC cannot be combined in a single published dataset; a NoDerivs clause silently prohibits tokenisation and annotation. This paper audits the license provenance of over twenty corpus families used in African NLP, constructs a six-tier compatibility matrix, and applies it to three case-study languages: Kituba/Munukutuba, Zarma, and Moore. Four failure modes are documented with primary-source evidence: outright prohibition (JW300, removed from OPUS after a legal aud"},"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":"2606.28867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T11:16:12Z","cross_cats_sorted":[],"title_canon_sha256":"b031af5f4ad840bc2723361ac5316ae77a94dc861001767f7a305319585cb0f9","abstract_canon_sha256":"2e3a0d3cf87c7e008eb999bb390a4e9723daea4cede315f5a6ccaafe8c8d3fea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:55.174143Z","signature_b64":"Aa+HdI3ffnn7to7lioFOprgpgi8dWfibxn1w8cGC6FcLgbUvmTNM0zJAGcuIw/nLVTDYkcBGrdnxW788dXMhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07ddf5c9cdbebdd575698be7b90a66fc1a1a9746effc2ef6ec47690bb84cd495","last_reissued_at":"2026-06-30T01:16:55.173663Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:55.173663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open but Incompatible: A License Compatibility Analysis of Corpora for Low-Resource African Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ernst van Gassen","submitted_at":"2026-06-27T11:16:12Z","abstract_excerpt":"Creative Commons licenses dominate African NLP corpus releases, but their compatibility rules are rarely applied. CC-BY-SA and CC-BY-NC cannot be combined in a single published dataset; a NoDerivs clause silently prohibits tokenisation and annotation. This paper audits the license provenance of over twenty corpus families used in African NLP, constructs a six-tier compatibility matrix, and applies it to three case-study languages: Kituba/Munukutuba, Zarma, and Moore. Four failure modes are documented with primary-source evidence: outright prohibition (JW300, removed from OPUS after a legal aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28867","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/2606.28867/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":"2606.28867","created_at":"2026-06-30T01:16:55.173738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28867v1","created_at":"2026-06-30T01:16:55.173738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28867","created_at":"2026-06-30T01:16:55.173738+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7O7LSONX265","created_at":"2026-06-30T01:16:55.173738+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7O7LSONX265K5LJ","created_at":"2026-06-30T01:16:55.173738+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7O7LSON","created_at":"2026-06-30T01:16:55.173738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.28867","citing_title":"Open but Incompatible: A License Compatibility Analysis of Corpora for Low-Resource African Languages","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q","json":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q.json","graph_json":"https://pith.science/api/pith-number/A7O7LSONX265K5LJRPT3SCTG7Q/graph.json","events_json":"https://pith.science/api/pith-number/A7O7LSONX265K5LJRPT3SCTG7Q/events.json","paper":"https://pith.science/paper/A7O7LSON"},"agent_actions":{"view_html":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q","download_json":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q.json","view_paper":"https://pith.science/paper/A7O7LSON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28867&json=true","fetch_graph":"https://pith.science/api/pith-number/A7O7LSONX265K5LJRPT3SCTG7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/A7O7LSONX265K5LJRPT3SCTG7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/action/storage_attestation","attest_author":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/action/author_attestation","sign_citation":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/action/citation_signature","submit_replication":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/action/replication_record"}},"created_at":"2026-06-30T01:16:55.173738+00:00","updated_at":"2026-06-30T01:16:55.173738+00:00"}