{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A7O7LSONX265K5LJRPT3SCTG7Q","short_pith_number":"pith:A7O7LSON","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"},"canonical_sha256":"07ddf5c9cdbebdd575698be7b90a66fc1a1a9746effc2ef6ec47690bb84cd495","source":{"kind":"arxiv","id":"2606.28867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28867","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28867v1","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28867","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"A7O7LSONX265","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"A7O7LSONX265K5LJ","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"A7O7LSON","created_at":"2026-06-30T01:16:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A7O7LSONX265K5LJRPT3SCTG7Q","target":"record","payload":{"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"},"canonical_sha256":"07ddf5c9cdbebdd575698be7b90a66fc1a1a9746effc2ef6ec47690bb84cd495","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"},"source_kind":"arxiv","source_id":"2606.28867","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:16:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eg0cEHu5tXMBVmKluy6d/z4PZUNeXcps72ruabUwS96nvV2B45m16DJAJtlXiAAAwZ0pYQQKYM5hOrTudqRlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T06:12:51.531123Z"},"content_sha256":"5fceccb2096eabc8278ef48c4c7be37d644ab84cef9cb5de17e3489e1b48fc54","schema_version":"1.0","event_id":"sha256:5fceccb2096eabc8278ef48c4c7be37d644ab84cef9cb5de17e3489e1b48fc54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A7O7LSONX265K5LJRPT3SCTG7Q","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:16:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2FpqhLfIidZkwcvmlKr69KpAxNzPtUtkdENqVXZS9XzZMyMd24/LgcTszaD++5381DquQQqcDY1yFZYTkPrhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T06:12:51.531522Z"},"content_sha256":"346bef9d10b8d8b8066b7ace84f201bed1b4d0494aac1f79c15ef766d4763038","schema_version":"1.0","event_id":"sha256:346bef9d10b8d8b8066b7ace84f201bed1b4d0494aac1f79c15ef766d4763038"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/bundle.json","state_url":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A7O7LSONX265K5LJRPT3SCTG7Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-03T06:12:51Z","links":{"resolver":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q","bundle":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/bundle.json","state":"https://pith.science/pith/A7O7LSONX265K5LJRPT3SCTG7Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A7O7LSONX265K5LJRPT3SCTG7Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A7O7LSONX265K5LJRPT3SCTG7Q","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":"2e3a0d3cf87c7e008eb999bb390a4e9723daea4cede315f5a6ccaafe8c8d3fea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T11:16:12Z","title_canon_sha256":"b031af5f4ad840bc2723361ac5316ae77a94dc861001767f7a305319585cb0f9"},"schema_version":"1.0","source":{"id":"2606.28867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28867","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28867v1","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28867","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"A7O7LSONX265","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"A7O7LSONX265K5LJ","created_at":"2026-06-30T01:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"A7O7LSON","created_at":"2026-06-30T01:16:55Z"}],"graph_snapshots":[{"event_id":"sha256:346bef9d10b8d8b8066b7ace84f201bed1b4d0494aac1f79c15ef766d4763038","target":"graph","created_at":"2026-06-30T01:16:55Z","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/2606.28867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ernst van Gassen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T11:16:12Z","title":"Open but Incompatible: A License Compatibility Analysis of Corpora for Low-Resource African Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28867","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":"sha256:5fceccb2096eabc8278ef48c4c7be37d644ab84cef9cb5de17e3489e1b48fc54","target":"record","created_at":"2026-06-30T01:16:55Z","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":"2e3a0d3cf87c7e008eb999bb390a4e9723daea4cede315f5a6ccaafe8c8d3fea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T11:16:12Z","title_canon_sha256":"b031af5f4ad840bc2723361ac5316ae77a94dc861001767f7a305319585cb0f9"},"schema_version":"1.0","source":{"id":"2606.28867","kind":"arxiv","version":1}},"canonical_sha256":"07ddf5c9cdbebdd575698be7b90a66fc1a1a9746effc2ef6ec47690bb84cd495","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07ddf5c9cdbebdd575698be7b90a66fc1a1a9746effc2ef6ec47690bb84cd495","first_computed_at":"2026-06-30T01:16:55.173663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:16:55.173663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Aa+HdI3ffnn7to7lioFOprgpgi8dWfibxn1w8cGC6FcLgbUvmTNM0zJAGcuIw/nLVTDYkcBGrdnxW788dXMhBQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:16:55.174143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fceccb2096eabc8278ef48c4c7be37d644ab84cef9cb5de17e3489e1b48fc54","sha256:346bef9d10b8d8b8066b7ace84f201bed1b4d0494aac1f79c15ef766d4763038"],"state_sha256":"7886b990cecb8ad4c98531cb8f8309306d0b223baa19f6e7f0fa12d9fa3370a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+0cvyymGzcFyAKcKDRpopgzELukB3cYnIhk7qzyQ24IGWjAgogwr0k0HQaEnyYRXf1wZOoJXi1f6rDQ5JV6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T06:12:51.533583Z","bundle_sha256":"892295d3b9f6f31c7a519cbe31de30fa5f894e5de3663fcc45a81576df829ff3"}}