{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FT3TF7LPSMVUQ6TI2V44H2NBJI","short_pith_number":"pith:FT3TF7LP","canonical_record":{"source":{"id":"2309.09950","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T17:13:50Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6fd31478cef21c3d78f0482886b3391dad567468ef787270cda92fe380058560","abstract_canon_sha256":"aec589cacec473cd804a00959367291771434e95b448be19eb24bb2eba1d77be"},"schema_version":"1.0"},"canonical_sha256":"2cf732fd6f932b487a68d579c3e9a14a24d6d672cf42f04cb18e8e4e27150d0e","source":{"kind":"arxiv","id":"2309.09950","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09950","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09950v2","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09950","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"pith_short_12","alias_value":"FT3TF7LPSMVU","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"pith_short_16","alias_value":"FT3TF7LPSMVUQ6TI","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"pith_short_8","alias_value":"FT3TF7LP","created_at":"2026-07-05T06:52:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FT3TF7LPSMVUQ6TI2V44H2NBJI","target":"record","payload":{"canonical_record":{"source":{"id":"2309.09950","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T17:13:50Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6fd31478cef21c3d78f0482886b3391dad567468ef787270cda92fe380058560","abstract_canon_sha256":"aec589cacec473cd804a00959367291771434e95b448be19eb24bb2eba1d77be"},"schema_version":"1.0"},"canonical_sha256":"2cf732fd6f932b487a68d579c3e9a14a24d6d672cf42f04cb18e8e4e27150d0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:50.248496Z","signature_b64":"H1aLmEgDV1h53XeVFQPogffl91tQ4/ML7mzwaPrmcQrF+c1Fw2oOHFNojyojGMjkmsaUlKQCtywdcUXxQOI/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf732fd6f932b487a68d579c3e9a14a24d6d672cf42f04cb18e8e4e27150d0e","last_reissued_at":"2026-07-05T06:52:50.248029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:50.248029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.09950","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":"2026-07-05T06:52:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Er6O1x//KSxWJxLbEsWRTjQL7CbdOiBibieJVfzk4dSXK760v1lb9dLKbjZnkMkGQdJv5StzmeE1L4MZeisiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:08:18.747041Z"},"content_sha256":"4960fefb8983f5a930bf2c81a2708042985645ad5de1df6c493abcfafc47490c","schema_version":"1.0","event_id":"sha256:4960fefb8983f5a930bf2c81a2708042985645ad5de1df6c493abcfafc47490c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FT3TF7LPSMVUQ6TI2V44H2NBJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating End-to-End ASR Architectures for Long Form Audio Transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Dima Rekesh, Georgy Zelenfroind, Jagadeesh Balam, Nithin Rao Koluguri, Samuel Kriman, Somshubra Majumdar, Vahid Noroozi","submitted_at":"2023-09-18T17:13:50Z","abstract_excerpt":"This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audios. We study three categories of Automatic Speech Recognition(ASR) models based on their core architecture: (1) convolutional, (2) convolutional with squeeze-and-excitation and (3) convolutional models with attention. We selected one ASR model from each category and evaluated Word Error Rate, maximum audio length and real-time factor for each model on a variety of long audio benchmarks: Earnings-21 and 22, CORAAL, and TED-LIUM3. The model from the category of self-attention with local attention"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09950","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/2309.09950/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":"2026-07-05T06:52:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9JsxcUPXZFJHXYvnyr2Q84CwS5QAtoyZ98ZpeajN/PQ2DZKkKTGnOK655Iz8xIR7EeWIg8Rd0Bv8TRz8JPG8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:08:18.747458Z"},"content_sha256":"c2df41c2cca33f7be002ec9b116a5556343e785abede1d2b3e9d806da2eb479f","schema_version":"1.0","event_id":"sha256:c2df41c2cca33f7be002ec9b116a5556343e785abede1d2b3e9d806da2eb479f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FT3TF7LPSMVUQ6TI2V44H2NBJI/bundle.json","state_url":"https://pith.science/pith/FT3TF7LPSMVUQ6TI2V44H2NBJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FT3TF7LPSMVUQ6TI2V44H2NBJI/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":"2026-07-06T09:08:18Z","links":{"resolver":"https://pith.science/pith/FT3TF7LPSMVUQ6TI2V44H2NBJI","bundle":"https://pith.science/pith/FT3TF7LPSMVUQ6TI2V44H2NBJI/bundle.json","state":"https://pith.science/pith/FT3TF7LPSMVUQ6TI2V44H2NBJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FT3TF7LPSMVUQ6TI2V44H2NBJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FT3TF7LPSMVUQ6TI2V44H2NBJI","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":"aec589cacec473cd804a00959367291771434e95b448be19eb24bb2eba1d77be","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T17:13:50Z","title_canon_sha256":"6fd31478cef21c3d78f0482886b3391dad567468ef787270cda92fe380058560"},"schema_version":"1.0","source":{"id":"2309.09950","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09950","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09950v2","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09950","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"pith_short_12","alias_value":"FT3TF7LPSMVU","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"pith_short_16","alias_value":"FT3TF7LPSMVUQ6TI","created_at":"2026-07-05T06:52:50Z"},{"alias_kind":"pith_short_8","alias_value":"FT3TF7LP","created_at":"2026-07-05T06:52:50Z"}],"graph_snapshots":[{"event_id":"sha256:c2df41c2cca33f7be002ec9b116a5556343e785abede1d2b3e9d806da2eb479f","target":"graph","created_at":"2026-07-05T06:52:50Z","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/2309.09950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audios. We study three categories of Automatic Speech Recognition(ASR) models based on their core architecture: (1) convolutional, (2) convolutional with squeeze-and-excitation and (3) convolutional models with attention. We selected one ASR model from each category and evaluated Word Error Rate, maximum audio length and real-time factor for each model on a variety of long audio benchmarks: Earnings-21 and 22, CORAAL, and TED-LIUM3. The model from the category of self-attention with local attention","authors_text":"Boris Ginsburg, Dima Rekesh, Georgy Zelenfroind, Jagadeesh Balam, Nithin Rao Koluguri, Samuel Kriman, Somshubra Majumdar, Vahid Noroozi","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T17:13:50Z","title":"Investigating End-to-End ASR Architectures for Long Form Audio Transcription"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09950","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":"sha256:4960fefb8983f5a930bf2c81a2708042985645ad5de1df6c493abcfafc47490c","target":"record","created_at":"2026-07-05T06:52:50Z","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":"aec589cacec473cd804a00959367291771434e95b448be19eb24bb2eba1d77be","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T17:13:50Z","title_canon_sha256":"6fd31478cef21c3d78f0482886b3391dad567468ef787270cda92fe380058560"},"schema_version":"1.0","source":{"id":"2309.09950","kind":"arxiv","version":2}},"canonical_sha256":"2cf732fd6f932b487a68d579c3e9a14a24d6d672cf42f04cb18e8e4e27150d0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cf732fd6f932b487a68d579c3e9a14a24d6d672cf42f04cb18e8e4e27150d0e","first_computed_at":"2026-07-05T06:52:50.248029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:50.248029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H1aLmEgDV1h53XeVFQPogffl91tQ4/ML7mzwaPrmcQrF+c1Fw2oOHFNojyojGMjkmsaUlKQCtywdcUXxQOI/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:50.248496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09950","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4960fefb8983f5a930bf2c81a2708042985645ad5de1df6c493abcfafc47490c","sha256:c2df41c2cca33f7be002ec9b116a5556343e785abede1d2b3e9d806da2eb479f"],"state_sha256":"04dd335d44d0e802c0820bbce97d0d67a73a23847d9930adfcac03df96adcb27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4T9ctxaOtpUni/szuH/ufkL0mlSgABseituo/QurPcKGWZ/W/sHzr80JnZ3jMwQPwnsAasANdaZuTefHgG5LCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T09:08:18.749437Z","bundle_sha256":"7992f98546d799aebcdb81af61ed849dbe9da26fa99e3adcbfe11f0990f9e772"}}