{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ICH4RDFZYJ2WBJDCXZIK7L7XRP","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":"39d7876af2b591f528d5523c0c73c902ffada5adc9f818053f4153f7051d00f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T18:49:55Z","title_canon_sha256":"e4551131f1f2bcb5d08f1831186fcfb4c7df151c8bf8d3f526be4026b22f6f3e"},"schema_version":"1.0","source":{"id":"2305.17202","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17202","created_at":"2026-07-05T06:14:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17202v1","created_at":"2026-07-05T06:14:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17202","created_at":"2026-07-05T06:14:25Z"},{"alias_kind":"pith_short_12","alias_value":"ICH4RDFZYJ2W","created_at":"2026-07-05T06:14:25Z"},{"alias_kind":"pith_short_16","alias_value":"ICH4RDFZYJ2WBJDC","created_at":"2026-07-05T06:14:25Z"},{"alias_kind":"pith_short_8","alias_value":"ICH4RDFZ","created_at":"2026-07-05T06:14:25Z"}],"graph_snapshots":[{"event_id":"sha256:d9726b332f24e23377bc71fe5c98159314fe49d06b3e6973208c2c20360afe7d","target":"graph","created_at":"2026-07-05T06:14:25Z","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/2305.17202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present BIG-C (Bemba Image Grounded Conversations), a large multimodal dataset for Bemba. While Bemba is the most populous language of Zambia, it exhibits a dearth of resources which render the development of language technologies or language processing research almost impossible. The dataset is comprised of multi-turn dialogues between Bemba speakers based on images, transcribed and translated into English. There are more than 92,000 utterances/sentences, amounting to more than 180 hours of audio data with corresponding transcriptions and English translations. We also provide baselines on ","authors_text":"Antonios Anastasopoulos, Claytone Sikasote, Eunice Mukonde, Md Mahfuz ibn Alam","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T18:49:55Z","title":"BIG-C: a Multimodal Multi-Purpose Dataset for Bemba"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17202","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":"sha256:24964d8f22ffcb70e4d0cb8fa0ea20158a28ff8d0c4ff3d57a53d884573b7d27","target":"record","created_at":"2026-07-05T06:14:25Z","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":"39d7876af2b591f528d5523c0c73c902ffada5adc9f818053f4153f7051d00f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T18:49:55Z","title_canon_sha256":"e4551131f1f2bcb5d08f1831186fcfb4c7df151c8bf8d3f526be4026b22f6f3e"},"schema_version":"1.0","source":{"id":"2305.17202","kind":"arxiv","version":1}},"canonical_sha256":"408fc88cb9c27560a462be50afaff78bfd810e535f9f8716b13e5e749cefc997","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"408fc88cb9c27560a462be50afaff78bfd810e535f9f8716b13e5e749cefc997","first_computed_at":"2026-07-05T06:14:25.154641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:25.154641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67djzi6tybf9u3L2tdCm3bmLE7rJdt1bGRDdR86LliL7dMfNuyf1lezbmuDismYgnHXbRpIyvxgfs2VLNpfNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:25.155115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17202","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24964d8f22ffcb70e4d0cb8fa0ea20158a28ff8d0c4ff3d57a53d884573b7d27","sha256:d9726b332f24e23377bc71fe5c98159314fe49d06b3e6973208c2c20360afe7d"],"state_sha256":"c6c0a410720eede6331660d88e2e8f9e06a8c7b6bf91c41dbda4c813aaf3b30b"}