{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:N7Y5CIIT4QY2AEEMBVWEY62Z6S","short_pith_number":"pith:N7Y5CIIT","canonical_record":{"source":{"id":"2111.09344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T19:14:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3b4d53a6952a2042262c9bdbe3d6b16b773e04fe77a1dc71fe422e28d01b9d61","abstract_canon_sha256":"e588971df9ba31e4e2852ec0902fa5afef54cea6f8eea4ee195b73160a78d50f"},"schema_version":"1.0"},"canonical_sha256":"6ff1d12113e431a0108c0d6c4c7b59f4811fb6669893a10ff3026fa3c792b20c","source":{"kind":"arxiv","id":"2111.09344","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09344","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09344v1","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09344","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"pith_short_12","alias_value":"N7Y5CIIT4QY2","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"N7Y5CIIT4QY2AEEM","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"N7Y5CIIT","created_at":"2026-07-05T03:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:N7Y5CIIT4QY2AEEMBVWEY62Z6S","target":"record","payload":{"canonical_record":{"source":{"id":"2111.09344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T19:14:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3b4d53a6952a2042262c9bdbe3d6b16b773e04fe77a1dc71fe422e28d01b9d61","abstract_canon_sha256":"e588971df9ba31e4e2852ec0902fa5afef54cea6f8eea4ee195b73160a78d50f"},"schema_version":"1.0"},"canonical_sha256":"6ff1d12113e431a0108c0d6c4c7b59f4811fb6669893a10ff3026fa3c792b20c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:10.274842Z","signature_b64":"LGJuJwl7iX8+nyVWdiDLcCgvrq3unppc8krOk++WwJfMFud0oJtqTXUeq4C++u5b2CF/UU4XD+cm+qP9bYZYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ff1d12113e431a0108c0d6c4c7b59f4811fb6669893a10ff3026fa3c792b20c","last_reissued_at":"2026-07-05T03:33:10.274346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:10.274346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.09344","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":"2026-07-05T03:33:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPJDLHSRCKCPmhlS24orjtD1tfwtJQf44kHoVE2Pn1OOSfuhHdQN0zDjxhhKIbiGXlaNIynNN6xLL+UNPX7bAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:55:37.557421Z"},"content_sha256":"b887d32889a083616850dd55fafd06b0ed42e2f0e69c4562afc6454e02e23ed3","schema_version":"1.0","event_id":"sha256:b887d32889a083616850dd55fafd06b0ed42e2f0e69c4562afc6454e02e23ed3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:N7Y5CIIT4QY2AEEMBVWEY62Z6S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anjali Gopi, Daniel Galvez, David Kanter, Greg Diamos, Juan Ciro, Juan Felipe Cer\\'on, Keith Achorn, Mark Mazumder, Maximilian Lam, Vijay Janapa Reddi","submitted_at":"2021-11-17T19:14:40Z","abstract_excerpt":"The People's Speech is a free-to-download 30,000-hour and growing supervised conversational English speech recognition dataset licensed for academic and commercial usage under CC-BY-SA (with a CC-BY subset). The data is collected via searching the Internet for appropriately licensed audio data with existing transcriptions. We describe our data collection methodology and release our data collection system under the Apache 2.0 license. We show that a model trained on this dataset achieves a 9.98% word error rate on Librispeech's test-clean test set.Finally, we discuss the legal and ethical issue"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09344","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/2111.09344/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":"2026-07-05T03:33:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"59mIWXifwaGVIewrQLK8lrWuVypL7lfDDra15z8gvVKO8nl7D5/PSOrh5jQZVvjH5sQ/BWHvdLZxFGyXtXMPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:55:37.557904Z"},"content_sha256":"74bdbce8f455db644a22e7621e4e14cdfd7ddab2930de9ccc19fb58331214b16","schema_version":"1.0","event_id":"sha256:74bdbce8f455db644a22e7621e4e14cdfd7ddab2930de9ccc19fb58331214b16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N7Y5CIIT4QY2AEEMBVWEY62Z6S/bundle.json","state_url":"https://pith.science/pith/N7Y5CIIT4QY2AEEMBVWEY62Z6S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N7Y5CIIT4QY2AEEMBVWEY62Z6S/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":"2026-08-03T15:55:37Z","links":{"resolver":"https://pith.science/pith/N7Y5CIIT4QY2AEEMBVWEY62Z6S","bundle":"https://pith.science/pith/N7Y5CIIT4QY2AEEMBVWEY62Z6S/bundle.json","state":"https://pith.science/pith/N7Y5CIIT4QY2AEEMBVWEY62Z6S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N7Y5CIIT4QY2AEEMBVWEY62Z6S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N7Y5CIIT4QY2AEEMBVWEY62Z6S","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":"e588971df9ba31e4e2852ec0902fa5afef54cea6f8eea4ee195b73160a78d50f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T19:14:40Z","title_canon_sha256":"3b4d53a6952a2042262c9bdbe3d6b16b773e04fe77a1dc71fe422e28d01b9d61"},"schema_version":"1.0","source":{"id":"2111.09344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09344","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09344v1","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09344","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"pith_short_12","alias_value":"N7Y5CIIT4QY2","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"N7Y5CIIT4QY2AEEM","created_at":"2026-07-05T03:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"N7Y5CIIT","created_at":"2026-07-05T03:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:74bdbce8f455db644a22e7621e4e14cdfd7ddab2930de9ccc19fb58331214b16","target":"graph","created_at":"2026-07-05T03:33:10Z","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/2111.09344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The People's Speech is a free-to-download 30,000-hour and growing supervised conversational English speech recognition dataset licensed for academic and commercial usage under CC-BY-SA (with a CC-BY subset). The data is collected via searching the Internet for appropriately licensed audio data with existing transcriptions. We describe our data collection methodology and release our data collection system under the Apache 2.0 license. We show that a model trained on this dataset achieves a 9.98% word error rate on Librispeech's test-clean test set.Finally, we discuss the legal and ethical issue","authors_text":"Anjali Gopi, Daniel Galvez, David Kanter, Greg Diamos, Juan Ciro, Juan Felipe Cer\\'on, Keith Achorn, Mark Mazumder, Maximilian Lam, Vijay Janapa Reddi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T19:14:40Z","title":"The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09344","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:b887d32889a083616850dd55fafd06b0ed42e2f0e69c4562afc6454e02e23ed3","target":"record","created_at":"2026-07-05T03:33:10Z","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":"e588971df9ba31e4e2852ec0902fa5afef54cea6f8eea4ee195b73160a78d50f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T19:14:40Z","title_canon_sha256":"3b4d53a6952a2042262c9bdbe3d6b16b773e04fe77a1dc71fe422e28d01b9d61"},"schema_version":"1.0","source":{"id":"2111.09344","kind":"arxiv","version":1}},"canonical_sha256":"6ff1d12113e431a0108c0d6c4c7b59f4811fb6669893a10ff3026fa3c792b20c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ff1d12113e431a0108c0d6c4c7b59f4811fb6669893a10ff3026fa3c792b20c","first_computed_at":"2026-07-05T03:33:10.274346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:10.274346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LGJuJwl7iX8+nyVWdiDLcCgvrq3unppc8krOk++WwJfMFud0oJtqTXUeq4C++u5b2CF/UU4XD+cm+qP9bYZYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:10.274842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b887d32889a083616850dd55fafd06b0ed42e2f0e69c4562afc6454e02e23ed3","sha256:74bdbce8f455db644a22e7621e4e14cdfd7ddab2930de9ccc19fb58331214b16"],"state_sha256":"a66b2e005c2e6625a8c55196defde0968a3c597b4ee6bf6184ab3e013a38e486"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zs+0Wy1xMNfuW+omYJXYxxozUYdOILDTOaTppRUCbp+tyx4vV8eEMAvnJ21nymH3AAMXouPfV4aM0IzUQ3O/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:55:37.561071Z","bundle_sha256":"7311539102fa0f7c6395bd35843da71a07c60ac72ce3a592d9ee01cbaa05ac61"}}