{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6SZHYFFZV7G2NVD4FEKMNSEKPH","short_pith_number":"pith:6SZHYFFZ","canonical_record":{"source":{"id":"2309.09843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T14:59:10Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"677c2b3735e43584440d1f328cb01dc91109faba3ceb82e825119dda8c4ffd8a","abstract_canon_sha256":"97179ff3944f20758c5fa7580627ad14bd4c087725647e6fe556ac05eaae0175"},"schema_version":"1.0"},"canonical_sha256":"f4b27c14b9afcda6d47c2914c6c88a79ca013402ee07d0291bd3280efe04b368","source":{"kind":"arxiv","id":"2309.09843","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09843","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09843v1","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09843","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"pith_short_12","alias_value":"6SZHYFFZV7G2","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"pith_short_16","alias_value":"6SZHYFFZV7G2NVD4","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"pith_short_8","alias_value":"6SZHYFFZ","created_at":"2026-07-05T06:51:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6SZHYFFZV7G2NVD4FEKMNSEKPH","target":"record","payload":{"canonical_record":{"source":{"id":"2309.09843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T14:59:10Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"677c2b3735e43584440d1f328cb01dc91109faba3ceb82e825119dda8c4ffd8a","abstract_canon_sha256":"97179ff3944f20758c5fa7580627ad14bd4c087725647e6fe556ac05eaae0175"},"schema_version":"1.0"},"canonical_sha256":"f4b27c14b9afcda6d47c2914c6c88a79ca013402ee07d0291bd3280efe04b368","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:45.296463Z","signature_b64":"eh4R5IHQDzNMC2hLdcagRoYQbzgmMmTIwoE6DWnhFbZUH6a3pi1WhKGmzvvnPJTU6IUKIJZMh/Eubds+sR4vBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b27c14b9afcda6d47c2914c6c88a79ca013402ee07d0291bd3280efe04b368","last_reissued_at":"2026-07-05T06:51:45.295965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:45.295965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.09843","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":"2026-07-05T06:51:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kBNUHa4oPFF8P2sNxiYBm79Fu48+OBoZsFlq7cZp6ssCbfHNZpsCrqkDOilvfoegamz+0BdVKbQJ+3dU8qCwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:18:49.807099Z"},"content_sha256":"82915655d4701d9487b70b7137b188acf18ccf4d8b94cd8cfabe8d0314b4e4a9","schema_version":"1.0","event_id":"sha256:82915655d4701d9487b70b7137b188acf18ccf4d8b94cd8cfabe8d0314b4e4a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6SZHYFFZV7G2NVD4FEKMNSEKPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instruction-Following Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cheng-I Jeff Lai, Liangliang Cao, Ruoming Pang, Zhiyun Lu","submitted_at":"2023-09-18T14:59:10Z","abstract_excerpt":"Conventional end-to-end Automatic Speech Recognition (ASR) models primarily focus on exact transcription tasks, lacking flexibility for nuanced user interactions. With the advent of Large Language Models (LLMs) in speech processing, more organic, text-prompt-based interactions have become possible. However, the mechanisms behind these models' speech understanding and \"reasoning\" capabilities remain underexplored. To study this question from the data perspective, we introduce instruction-following speech recognition, training a Listen-Attend-Spell model to understand and execute a diverse set o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09843","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/2309.09843/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":"2026-07-05T06:51:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afOwG75Dq1zKAAwCHVCoiKXqZHNlV+2kN1Yov6HfFGR+H2ROEcQ3A2YRDP13YAaBeC1A64g0Q6Hllt28UFMjAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:18:49.807548Z"},"content_sha256":"7f95dcbaf33edf0203e76b851aad9197450d4125c269ebf0ddea51a44c1c37ad","schema_version":"1.0","event_id":"sha256:7f95dcbaf33edf0203e76b851aad9197450d4125c269ebf0ddea51a44c1c37ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SZHYFFZV7G2NVD4FEKMNSEKPH/bundle.json","state_url":"https://pith.science/pith/6SZHYFFZV7G2NVD4FEKMNSEKPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SZHYFFZV7G2NVD4FEKMNSEKPH/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":"2026-07-31T14:18:49Z","links":{"resolver":"https://pith.science/pith/6SZHYFFZV7G2NVD4FEKMNSEKPH","bundle":"https://pith.science/pith/6SZHYFFZV7G2NVD4FEKMNSEKPH/bundle.json","state":"https://pith.science/pith/6SZHYFFZV7G2NVD4FEKMNSEKPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SZHYFFZV7G2NVD4FEKMNSEKPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6SZHYFFZV7G2NVD4FEKMNSEKPH","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":"97179ff3944f20758c5fa7580627ad14bd4c087725647e6fe556ac05eaae0175","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T14:59:10Z","title_canon_sha256":"677c2b3735e43584440d1f328cb01dc91109faba3ceb82e825119dda8c4ffd8a"},"schema_version":"1.0","source":{"id":"2309.09843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09843","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09843v1","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09843","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"pith_short_12","alias_value":"6SZHYFFZV7G2","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"pith_short_16","alias_value":"6SZHYFFZV7G2NVD4","created_at":"2026-07-05T06:51:45Z"},{"alias_kind":"pith_short_8","alias_value":"6SZHYFFZ","created_at":"2026-07-05T06:51:45Z"}],"graph_snapshots":[{"event_id":"sha256:7f95dcbaf33edf0203e76b851aad9197450d4125c269ebf0ddea51a44c1c37ad","target":"graph","created_at":"2026-07-05T06:51:45Z","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/2309.09843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional end-to-end Automatic Speech Recognition (ASR) models primarily focus on exact transcription tasks, lacking flexibility for nuanced user interactions. With the advent of Large Language Models (LLMs) in speech processing, more organic, text-prompt-based interactions have become possible. However, the mechanisms behind these models' speech understanding and \"reasoning\" capabilities remain underexplored. To study this question from the data perspective, we introduce instruction-following speech recognition, training a Listen-Attend-Spell model to understand and execute a diverse set o","authors_text":"Cheng-I Jeff Lai, Liangliang Cao, Ruoming Pang, Zhiyun Lu","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T14:59:10Z","title":"Instruction-Following Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09843","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":"sha256:82915655d4701d9487b70b7137b188acf18ccf4d8b94cd8cfabe8d0314b4e4a9","target":"record","created_at":"2026-07-05T06:51:45Z","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":"97179ff3944f20758c5fa7580627ad14bd4c087725647e6fe556ac05eaae0175","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T14:59:10Z","title_canon_sha256":"677c2b3735e43584440d1f328cb01dc91109faba3ceb82e825119dda8c4ffd8a"},"schema_version":"1.0","source":{"id":"2309.09843","kind":"arxiv","version":1}},"canonical_sha256":"f4b27c14b9afcda6d47c2914c6c88a79ca013402ee07d0291bd3280efe04b368","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4b27c14b9afcda6d47c2914c6c88a79ca013402ee07d0291bd3280efe04b368","first_computed_at":"2026-07-05T06:51:45.295965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:45.295965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eh4R5IHQDzNMC2hLdcagRoYQbzgmMmTIwoE6DWnhFbZUH6a3pi1WhKGmzvvnPJTU6IUKIJZMh/Eubds+sR4vBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:45.296463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82915655d4701d9487b70b7137b188acf18ccf4d8b94cd8cfabe8d0314b4e4a9","sha256:7f95dcbaf33edf0203e76b851aad9197450d4125c269ebf0ddea51a44c1c37ad"],"state_sha256":"650f7a3d257e1a30051d9e7f7490dd9b12cd70657296702784c63d225b2ab693"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xUJ6yzbvC3Z82IXr1zrT3+NvhJh7Z4+mCwMM01R9hGWbhmYHlk8dKP3zCZOqjGrgP99F88kF/oJgwhqY+wHDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:18:49.811661Z","bundle_sha256":"9c6a19026f5e37b26d4cdf23e3b0f73509de201c670849226e3b6fc1b2a01b1b"}}