{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WW4Z7KHIPL2FTYJUMNPXEYHXYN","short_pith_number":"pith:WW4Z7KHI","canonical_record":{"source":{"id":"2404.09841","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-15T14:48:43Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"e529b5b5ee6fd3a1bf2e63d5cf52aa9fecee603e35d16f24870a1019337eb18a","abstract_canon_sha256":"e79a7271f307cee751b5446fb8dc831be738748bcb5f1894bbb7ed0c384f4f60"},"schema_version":"1.0"},"canonical_sha256":"b5b99fa8e87af459e134635f7260f7c35efaff748bd424ccbf12baf88a40195c","source":{"kind":"arxiv","id":"2404.09841","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09841","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09841v2","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09841","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"WW4Z7KHIPL2F","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"WW4Z7KHIPL2FTYJU","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"WW4Z7KHI","created_at":"2026-07-05T08:08:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WW4Z7KHIPL2FTYJUMNPXEYHXYN","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09841","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-15T14:48:43Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"e529b5b5ee6fd3a1bf2e63d5cf52aa9fecee603e35d16f24870a1019337eb18a","abstract_canon_sha256":"e79a7271f307cee751b5446fb8dc831be738748bcb5f1894bbb7ed0c384f4f60"},"schema_version":"1.0"},"canonical_sha256":"b5b99fa8e87af459e134635f7260f7c35efaff748bd424ccbf12baf88a40195c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:41.758287Z","signature_b64":"gRbbhrnCxrQKx11qmjv6P6MOyQkTe5disf80ciC6tBA8eG+Jnzf3KScJMeDD+J8+e+T9kInWTPINXQsVRbZ3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5b99fa8e87af459e134635f7260f7c35efaff748bd424ccbf12baf88a40195c","last_reissued_at":"2026-07-05T08:08:41.757791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:41.757791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09841","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:08:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WVlWK8Ujjlmfn1qeBYnrBXY42RO6E9I7HI38p/1h943ZNThkr/d11aLHeH8DqLYmiW9griv5I/Xu0hkXGzx4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:42:18.074017Z"},"content_sha256":"27bb0512128e65cdd9db0122751b3e71da39250b6e355bf2135e774696bb4066","schema_version":"1.0","event_id":"sha256:27bb0512128e65cdd9db0122751b3e71da39250b6e355bf2135e774696bb4066"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WW4Z7KHIPL2FTYJUMNPXEYHXYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Anatomy of Industrial Scale Multilingual ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed Etefy, Andrea Vanzo, Andrew Ehrenberg, Daniel McCrystal, Domenic Donato, Enver Fakhan, Francis McCann Ramirez, Gabriel Oexle, Ilya Sklyar, Luka Chkhetiani, Michael Liang, Rami Botros, Robert McHardy, Sam Flamini, Takuya Yoshioka, Taufiquzzaman Peyash, Yash Khare","submitted_at":"2024-04-15T14:48:43Z","abstract_excerpt":"This paper describes AssemblyAI's industrial-scale automatic speech recognition (ASR) system, designed to meet the requirements of large-scale, multilingual ASR serving various application needs. Our system leverages a diverse training dataset comprising unsupervised (12.5M hours), supervised (188k hours), and pseudo-labeled (1.6M hours) data across four languages. We provide a detailed description of our model architecture, consisting of a full-context 600M-parameter Conformer encoder pre-trained with BEST-RQ and an RNN-T decoder fine-tuned jointly with the encoder. Our extensive evaluation d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09841","kind":"arxiv","version":2},"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/2404.09841/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":"2026-07-05T08:08:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5rNLhNhH1jIliDxfbOjmLQAjTY2PVSr75N2w3VblU2gtM9FJlHkFVZPSoD6Uu80VG1QyowGR3SRHFEN9GUE3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:42:18.074593Z"},"content_sha256":"59b8702215799ae51ec5a2227a43b9a6c61dc27f44c902791555220cbed0c4e6","schema_version":"1.0","event_id":"sha256:59b8702215799ae51ec5a2227a43b9a6c61dc27f44c902791555220cbed0c4e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WW4Z7KHIPL2FTYJUMNPXEYHXYN/bundle.json","state_url":"https://pith.science/pith/WW4Z7KHIPL2FTYJUMNPXEYHXYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WW4Z7KHIPL2FTYJUMNPXEYHXYN/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":"2026-08-08T19:42:18Z","links":{"resolver":"https://pith.science/pith/WW4Z7KHIPL2FTYJUMNPXEYHXYN","bundle":"https://pith.science/pith/WW4Z7KHIPL2FTYJUMNPXEYHXYN/bundle.json","state":"https://pith.science/pith/WW4Z7KHIPL2FTYJUMNPXEYHXYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WW4Z7KHIPL2FTYJUMNPXEYHXYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WW4Z7KHIPL2FTYJUMNPXEYHXYN","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":"e79a7271f307cee751b5446fb8dc831be738748bcb5f1894bbb7ed0c384f4f60","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-15T14:48:43Z","title_canon_sha256":"e529b5b5ee6fd3a1bf2e63d5cf52aa9fecee603e35d16f24870a1019337eb18a"},"schema_version":"1.0","source":{"id":"2404.09841","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09841","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09841v2","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09841","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"WW4Z7KHIPL2F","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"WW4Z7KHIPL2FTYJU","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"WW4Z7KHI","created_at":"2026-07-05T08:08:41Z"}],"graph_snapshots":[{"event_id":"sha256:59b8702215799ae51ec5a2227a43b9a6c61dc27f44c902791555220cbed0c4e6","target":"graph","created_at":"2026-07-05T08:08:41Z","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/2404.09841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes AssemblyAI's industrial-scale automatic speech recognition (ASR) system, designed to meet the requirements of large-scale, multilingual ASR serving various application needs. Our system leverages a diverse training dataset comprising unsupervised (12.5M hours), supervised (188k hours), and pseudo-labeled (1.6M hours) data across four languages. We provide a detailed description of our model architecture, consisting of a full-context 600M-parameter Conformer encoder pre-trained with BEST-RQ and an RNN-T decoder fine-tuned jointly with the encoder. Our extensive evaluation d","authors_text":"Ahmed Etefy, Andrea Vanzo, Andrew Ehrenberg, Daniel McCrystal, Domenic Donato, Enver Fakhan, Francis McCann Ramirez, Gabriel Oexle, Ilya Sklyar, Luka Chkhetiani, Michael Liang, Rami Botros, Robert McHardy, Sam Flamini, Takuya Yoshioka, Taufiquzzaman Peyash, Yash Khare","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-15T14:48:43Z","title":"Anatomy of Industrial Scale Multilingual ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09841","kind":"arxiv","version":2},"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":"sha256:27bb0512128e65cdd9db0122751b3e71da39250b6e355bf2135e774696bb4066","target":"record","created_at":"2026-07-05T08:08:41Z","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":"e79a7271f307cee751b5446fb8dc831be738748bcb5f1894bbb7ed0c384f4f60","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-15T14:48:43Z","title_canon_sha256":"e529b5b5ee6fd3a1bf2e63d5cf52aa9fecee603e35d16f24870a1019337eb18a"},"schema_version":"1.0","source":{"id":"2404.09841","kind":"arxiv","version":2}},"canonical_sha256":"b5b99fa8e87af459e134635f7260f7c35efaff748bd424ccbf12baf88a40195c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5b99fa8e87af459e134635f7260f7c35efaff748bd424ccbf12baf88a40195c","first_computed_at":"2026-07-05T08:08:41.757791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:41.757791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gRbbhrnCxrQKx11qmjv6P6MOyQkTe5disf80ciC6tBA8eG+Jnzf3KScJMeDD+J8+e+T9kInWTPINXQsVRbZ3BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:41.758287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09841","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27bb0512128e65cdd9db0122751b3e71da39250b6e355bf2135e774696bb4066","sha256:59b8702215799ae51ec5a2227a43b9a6c61dc27f44c902791555220cbed0c4e6"],"state_sha256":"0f36955ebbe6bf576ed655c0947eac422ea656191cb7894c6572e55b64c37d36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jWEPbI4Q/6JOQTjLWQ7+G1s1xSI44sMPunPj0Xv3e/oU7AVlUJaNgUVPzz+Gc1Rja41b+Qt623rilqYr/QL7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:42:18.079084Z","bundle_sha256":"2d8a38c083ef87fe7fd59d7ddd4d919f62b927d3ed279707c6cd9767ebf12a31"}}