{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:M3TF6CYIXEGIAHNQBT3VVULUQA","short_pith_number":"pith:M3TF6CYI","canonical_record":{"source":{"id":"2105.04674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T21:16:28Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"764e73c4760d8520678aa43a3f98cb38dbe8a962ffcce88e84d91b635afae005","abstract_canon_sha256":"e1c155326fbc1c51a27a4e99acb33e46349dfb89ae9959e2a58e6e700f8a5e85"},"schema_version":"1.0"},"canonical_sha256":"66e65f0b08b90c801db00cf75ad1748023776142f4caacc508eee94acb1f2b79","source":{"kind":"arxiv","id":"2105.04674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.04674","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2105.04674v1","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04674","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"M3TF6CYIXEGI","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"M3TF6CYIXEGIAHNQ","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"M3TF6CYI","created_at":"2026-07-05T02:39:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:M3TF6CYIXEGIAHNQBT3VVULUQA","target":"record","payload":{"canonical_record":{"source":{"id":"2105.04674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T21:16:28Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"764e73c4760d8520678aa43a3f98cb38dbe8a962ffcce88e84d91b635afae005","abstract_canon_sha256":"e1c155326fbc1c51a27a4e99acb33e46349dfb89ae9959e2a58e6e700f8a5e85"},"schema_version":"1.0"},"canonical_sha256":"66e65f0b08b90c801db00cf75ad1748023776142f4caacc508eee94acb1f2b79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:22.928885Z","signature_b64":"8gOcS3ktoETIM9SSnhJX5geel13Ct3ozBv7dc4VylZt2e8PEQ6F+64mlJ/XFUYdvBv0ECEvmxVlN60/ctVfNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e65f0b08b90c801db00cf75ad1748023776142f4caacc508eee94acb1f2b79","last_reissued_at":"2026-07-05T02:39:22.928530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:22.928530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.04674","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":"2026-07-05T02:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PXzHqKpaJTPvJ/6v+E++5hrJ9cusREbLvSXXfB2tMlP7kOfeBa8tqrXQTG+TedTtFR7UWAKPpwZkIPgJODDSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:06:17.946289Z"},"content_sha256":"9d6545ba1b3bb3205be1ed9908184d86a4ef24d0abae7d1fb6c0bce241b0b0cd","schema_version":"1.0","event_id":"sha256:9d6545ba1b3bb3205be1ed9908184d86a4ef24d0abae7d1fb6c0bce241b0b0cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:M3TF6CYIXEGIAHNQBT3VVULUQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What shall we do with an hour of data? Speech recognition for the un- and under-served languages of Common Voice","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Francis M. Tyers, Josh Meyer","submitted_at":"2021-05-10T21:16:28Z","abstract_excerpt":"This technical report describes the methods and results of a three-week sprint to produce deployable speech recognition models for 31 under-served languages of the Common Voice project. We outline the preprocessing steps, hyperparameter selection, and resulting accuracy on official testing sets. In addition to this we evaluate the models on multiple tasks: closed-vocabulary speech recognition, pre-transcription, forced alignment, and key-word spotting. The following experiments use Coqui STT, a toolkit for training and deployment of neural Speech-to-Text models."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04674","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/2105.04674/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":"2026-07-05T02:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f/04HiP9H5krpMiTW59x0CxI1ASCPe+Jr6IjREklVRrDZqnJbxKLw3ZREv+qsicHDl4vf/9UAYWn/mYziUwADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:06:17.946688Z"},"content_sha256":"e2fae1d29b85433e1a4bef2dc65ce991447f4b32bbd8c8a1801e4e874c4bcb3a","schema_version":"1.0","event_id":"sha256:e2fae1d29b85433e1a4bef2dc65ce991447f4b32bbd8c8a1801e4e874c4bcb3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3TF6CYIXEGIAHNQBT3VVULUQA/bundle.json","state_url":"https://pith.science/pith/M3TF6CYIXEGIAHNQBT3VVULUQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3TF6CYIXEGIAHNQBT3VVULUQA/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":"2026-08-05T03:06:17Z","links":{"resolver":"https://pith.science/pith/M3TF6CYIXEGIAHNQBT3VVULUQA","bundle":"https://pith.science/pith/M3TF6CYIXEGIAHNQBT3VVULUQA/bundle.json","state":"https://pith.science/pith/M3TF6CYIXEGIAHNQBT3VVULUQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3TF6CYIXEGIAHNQBT3VVULUQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M3TF6CYIXEGIAHNQBT3VVULUQA","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":"e1c155326fbc1c51a27a4e99acb33e46349dfb89ae9959e2a58e6e700f8a5e85","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T21:16:28Z","title_canon_sha256":"764e73c4760d8520678aa43a3f98cb38dbe8a962ffcce88e84d91b635afae005"},"schema_version":"1.0","source":{"id":"2105.04674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.04674","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2105.04674v1","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04674","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"M3TF6CYIXEGI","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"M3TF6CYIXEGIAHNQ","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"M3TF6CYI","created_at":"2026-07-05T02:39:22Z"}],"graph_snapshots":[{"event_id":"sha256:e2fae1d29b85433e1a4bef2dc65ce991447f4b32bbd8c8a1801e4e874c4bcb3a","target":"graph","created_at":"2026-07-05T02:39:22Z","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/2105.04674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This technical report describes the methods and results of a three-week sprint to produce deployable speech recognition models for 31 under-served languages of the Common Voice project. We outline the preprocessing steps, hyperparameter selection, and resulting accuracy on official testing sets. In addition to this we evaluate the models on multiple tasks: closed-vocabulary speech recognition, pre-transcription, forced alignment, and key-word spotting. The following experiments use Coqui STT, a toolkit for training and deployment of neural Speech-to-Text models.","authors_text":"Francis M. Tyers, Josh Meyer","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T21:16:28Z","title":"What shall we do with an hour of data? Speech recognition for the un- and under-served languages of Common Voice"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04674","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":"sha256:9d6545ba1b3bb3205be1ed9908184d86a4ef24d0abae7d1fb6c0bce241b0b0cd","target":"record","created_at":"2026-07-05T02:39:22Z","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":"e1c155326fbc1c51a27a4e99acb33e46349dfb89ae9959e2a58e6e700f8a5e85","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T21:16:28Z","title_canon_sha256":"764e73c4760d8520678aa43a3f98cb38dbe8a962ffcce88e84d91b635afae005"},"schema_version":"1.0","source":{"id":"2105.04674","kind":"arxiv","version":1}},"canonical_sha256":"66e65f0b08b90c801db00cf75ad1748023776142f4caacc508eee94acb1f2b79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66e65f0b08b90c801db00cf75ad1748023776142f4caacc508eee94acb1f2b79","first_computed_at":"2026-07-05T02:39:22.928530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:39:22.928530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8gOcS3ktoETIM9SSnhJX5geel13Ct3ozBv7dc4VylZt2e8PEQ6F+64mlJ/XFUYdvBv0ECEvmxVlN60/ctVfNBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:39:22.928885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.04674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d6545ba1b3bb3205be1ed9908184d86a4ef24d0abae7d1fb6c0bce241b0b0cd","sha256:e2fae1d29b85433e1a4bef2dc65ce991447f4b32bbd8c8a1801e4e874c4bcb3a"],"state_sha256":"e4c4d49f2f5e883d6d55e732b7875c63cd5cde4ec340fbb5fb339cb0e5d89fc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vlTIybBAQA5YPBlFihd6Db4+56gbrSFQ6ItbPy0asN3VonB64I6RTbXqrYa/mMNsgUbP68BUGlDWQD2vNtw2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:06:17.949398Z","bundle_sha256":"28a85cdcf387d9866fcbad0509c8bc94c3f9e645e2de5ecb8941218fa5b1a2c0"}}