{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QVI7W7BO2Z2GB7SQK4LEVWW46Q","short_pith_number":"pith:QVI7W7BO","canonical_record":{"source":{"id":"2607.18912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T09:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"863488b281094370ea4f864aa406fe9ee5c24289e5c13988d161657faafaebb4","abstract_canon_sha256":"14c199fbb7dd83522f5c39e6cc66793beb2fd746685cfe57dab335a7260a4cc9"},"schema_version":"1.0"},"canonical_sha256":"8551fb7c2ed67460fe5057164adadcf42819f2a89dd3999e8fb8d450f068bc87","source":{"kind":"arxiv","id":"2607.18912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18912","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18912v1","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18912","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"QVI7W7BO2Z2G","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"QVI7W7BO2Z2GB7SQ","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"QVI7W7BO","created_at":"2026-07-22T01:23:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QVI7W7BO2Z2GB7SQK4LEVWW46Q","target":"record","payload":{"canonical_record":{"source":{"id":"2607.18912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T09:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"863488b281094370ea4f864aa406fe9ee5c24289e5c13988d161657faafaebb4","abstract_canon_sha256":"14c199fbb7dd83522f5c39e6cc66793beb2fd746685cfe57dab335a7260a4cc9"},"schema_version":"1.0"},"canonical_sha256":"8551fb7c2ed67460fe5057164adadcf42819f2a89dd3999e8fb8d450f068bc87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:19.422375Z","signature_b64":"cL7GtYoQxWhVW7DbU9uYGsh8hbRHxmv1CYxbuM6gqV06kS6htErIQ91GQK3+ETYI972xT79fdEKcTiAtWolzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8551fb7c2ed67460fe5057164adadcf42819f2a89dd3999e8fb8d450f068bc87","last_reissued_at":"2026-07-22T01:23:19.421555Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:19.421555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.18912","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":"2026-07-22T01:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGJRImxxzUwPs5HPaEbUImHNq/YIsHCcD9gqEHTT+ANq32w6NLYn0AW4QnkFZFvDl+h+3ae9DUAnXQ/di22LCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:22:51.065651Z"},"content_sha256":"c097f26c0e8d0255a188375be23d84cff2c25ecb6bf3007eb0f130831e624617","schema_version":"1.0","event_id":"sha256:c097f26c0e8d0255a188375be23d84cff2c25ecb6bf3007eb0f130831e624617"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QVI7W7BO2Z2GB7SQK4LEVWW46Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From a Multilingual Streaming ASR Backbone to Kenyan-Language Systems: Data-Centric Adaptation of Nemotron 3.5 for Kikuyu, Dholuo, and Kalenjin","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mark Gatere","submitted_at":"2026-07-21T09:52:57Z","abstract_excerpt":"Automatic speech recognition (ASR) for African languages is constrained by orthographic inconsistency, annotation artifacts, missing audio, speaker and domain imbalance, and evaluation procedures that differ from deployment. We present an end-to-end engineering study adapting NVIDIA Nemotron 3.5 ASR Streaming 0.6B to Kikuyu, Dholuo, and Kalenjin. Starting from a Kenyan Swahili-adapted checkpoint, we retain its cache-aware FastConformer RNN-T, prompt conditioning, and streaming decoder during full-parameter fine-tuning. The study covers corpus auditing, Unicode normalization, split checks, dura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18912","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/2607.18912/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":"2026-07-22T01:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LAYpi/cHoasa0oqxESyr44JkKAbNFhysKLCkdTlaN7rl7Oa2qryFhxCRguH6IrZO1b5iQeDVzT/sGY7P1tufAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:22:51.066176Z"},"content_sha256":"614a34edcb48708fdf4d8b65cc4c596669e4c850a63fe807518b0784ac56dc4e","schema_version":"1.0","event_id":"sha256:614a34edcb48708fdf4d8b65cc4c596669e4c850a63fe807518b0784ac56dc4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVI7W7BO2Z2GB7SQK4LEVWW46Q/bundle.json","state_url":"https://pith.science/pith/QVI7W7BO2Z2GB7SQK4LEVWW46Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVI7W7BO2Z2GB7SQK4LEVWW46Q/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":"2026-08-05T02:22:51Z","links":{"resolver":"https://pith.science/pith/QVI7W7BO2Z2GB7SQK4LEVWW46Q","bundle":"https://pith.science/pith/QVI7W7BO2Z2GB7SQK4LEVWW46Q/bundle.json","state":"https://pith.science/pith/QVI7W7BO2Z2GB7SQK4LEVWW46Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVI7W7BO2Z2GB7SQK4LEVWW46Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QVI7W7BO2Z2GB7SQK4LEVWW46Q","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":"14c199fbb7dd83522f5c39e6cc66793beb2fd746685cfe57dab335a7260a4cc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T09:52:57Z","title_canon_sha256":"863488b281094370ea4f864aa406fe9ee5c24289e5c13988d161657faafaebb4"},"schema_version":"1.0","source":{"id":"2607.18912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18912","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18912v1","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18912","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"QVI7W7BO2Z2G","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"QVI7W7BO2Z2GB7SQ","created_at":"2026-07-22T01:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"QVI7W7BO","created_at":"2026-07-22T01:23:19Z"}],"graph_snapshots":[{"event_id":"sha256:614a34edcb48708fdf4d8b65cc4c596669e4c850a63fe807518b0784ac56dc4e","target":"graph","created_at":"2026-07-22T01:23:19Z","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/2607.18912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic speech recognition (ASR) for African languages is constrained by orthographic inconsistency, annotation artifacts, missing audio, speaker and domain imbalance, and evaluation procedures that differ from deployment. We present an end-to-end engineering study adapting NVIDIA Nemotron 3.5 ASR Streaming 0.6B to Kikuyu, Dholuo, and Kalenjin. Starting from a Kenyan Swahili-adapted checkpoint, we retain its cache-aware FastConformer RNN-T, prompt conditioning, and streaming decoder during full-parameter fine-tuning. The study covers corpus auditing, Unicode normalization, split checks, dura","authors_text":"Mark Gatere","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T09:52:57Z","title":"From a Multilingual Streaming ASR Backbone to Kenyan-Language Systems: Data-Centric Adaptation of Nemotron 3.5 for Kikuyu, Dholuo, and Kalenjin"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18912","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:c097f26c0e8d0255a188375be23d84cff2c25ecb6bf3007eb0f130831e624617","target":"record","created_at":"2026-07-22T01:23:19Z","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":"14c199fbb7dd83522f5c39e6cc66793beb2fd746685cfe57dab335a7260a4cc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T09:52:57Z","title_canon_sha256":"863488b281094370ea4f864aa406fe9ee5c24289e5c13988d161657faafaebb4"},"schema_version":"1.0","source":{"id":"2607.18912","kind":"arxiv","version":1}},"canonical_sha256":"8551fb7c2ed67460fe5057164adadcf42819f2a89dd3999e8fb8d450f068bc87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8551fb7c2ed67460fe5057164adadcf42819f2a89dd3999e8fb8d450f068bc87","first_computed_at":"2026-07-22T01:23:19.421555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:23:19.421555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cL7GtYoQxWhVW7DbU9uYGsh8hbRHxmv1CYxbuM6gqV06kS6htErIQ91GQK3+ETYI972xT79fdEKcTiAtWolzAQ==","signature_status":"signed_v1","signed_at":"2026-07-22T01:23:19.422375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c097f26c0e8d0255a188375be23d84cff2c25ecb6bf3007eb0f130831e624617","sha256:614a34edcb48708fdf4d8b65cc4c596669e4c850a63fe807518b0784ac56dc4e"],"state_sha256":"8ea80b5d2a4ba18a90fbfe5f9f9fc9982497537e59565dcd595f63e44ccd7a45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B1V+fCfQShGXYhRq5Uh+huDx3mwvGsosHyD5+FO42m7oBslD1zDOluUEZONX0s0m+vVYBdQ9II+EqgY92Cg+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:22:51.074406Z","bundle_sha256":"2a9b1fedf8cd35d77a1ed95f08778a341bbb3a89efd0823e8b7b8496d6a96ead"}}