{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S6PZHZKJILYAR4VCVVNCUJUAZ2","short_pith_number":"pith:S6PZHZKJ","canonical_record":{"source":{"id":"2406.03791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T07:03:28Z","cross_cats_sorted":[],"title_canon_sha256":"4d16577e2b99fa90afc48e22ae2e570911bc2621274cb41bb1ff108b2be2437c","abstract_canon_sha256":"4519d445edf69f43aa0e195cbb5335aea21d60b9adb7de13d813e851ff87dca8"},"schema_version":"1.0"},"canonical_sha256":"979f93e54942f008f2a2ad5a2a2680cea42f56a837bf530ac07c4d5b191e18be","source":{"kind":"arxiv","id":"2406.03791","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03791","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03791v1","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03791","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"S6PZHZKJILYA","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"S6PZHZKJILYAR4VC","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"S6PZHZKJ","created_at":"2026-07-05T08:28:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S6PZHZKJILYAR4VCVVNCUJUAZ2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T07:03:28Z","cross_cats_sorted":[],"title_canon_sha256":"4d16577e2b99fa90afc48e22ae2e570911bc2621274cb41bb1ff108b2be2437c","abstract_canon_sha256":"4519d445edf69f43aa0e195cbb5335aea21d60b9adb7de13d813e851ff87dca8"},"schema_version":"1.0"},"canonical_sha256":"979f93e54942f008f2a2ad5a2a2680cea42f56a837bf530ac07c4d5b191e18be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:15.961971Z","signature_b64":"PL0/mEKC3J0LS5f9AwDkhcL9DtL/ilL24o8E2TmEEJ7K7Kzo+/p5RJKCgJmUnN/Zoro9TteLvOLrdszh6zJODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"979f93e54942f008f2a2ad5a2a2680cea42f56a837bf530ac07c4d5b191e18be","last_reissued_at":"2026-07-05T08:28:15.961593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:15.961593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03791","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":"2026-07-05T08:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IYam4xFQVcRq/QVrb90EwGvXM+KZgGUrfCz/4vqEDzYYmHBIyCVHVaVY0+VidJ1d3u/S4qh0VR0JJZOQM0iFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:51:51.607826Z"},"content_sha256":"59c4cd28aff0bd7528f9e7e4288b4e55f4e141c5b95f4adb617eed7fe8786d01","schema_version":"1.0","event_id":"sha256:59c4cd28aff0bd7528f9e7e4288b4e55f4e141c5b95f4adb617eed7fe8786d01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S6PZHZKJILYAR4VCVVNCUJUAZ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Galvez, Hainan Xu, Tim Kaldewey, Vladimir Bataev","submitted_at":"2024-06-06T07:03:28Z","abstract_excerpt":"The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of the time. Leveraging a new CUDA 12.4 feature, CUDA graph conditional nodes, we present an exact GPU-based implementation of greedy decoding for RNN-T models that eliminates this idle time. Our optimizations speed up a 1.1 billion parameter RNN-T model end-to-end by a factor of 2.5x. This technique can applied to the \"label looping\" alternative greedy decoding algorithm as well, achieving 1.7x and 1.4x end-to-end spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03791","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/2406.03791/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":"2026-07-05T08:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YhdXuQ03gcPefruFAgY4H6W8VrP4VYMJBGl7Wl0YwvhwA3rVTXmHDuqJ6VWID6wJB4Qp9N+69S6mqrlSBkuBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:51:51.608331Z"},"content_sha256":"14cd705b3a857d16e81a41529fb6e0602d944606eb9183d65fa793141ab55d50","schema_version":"1.0","event_id":"sha256:14cd705b3a857d16e81a41529fb6e0602d944606eb9183d65fa793141ab55d50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6PZHZKJILYAR4VCVVNCUJUAZ2/bundle.json","state_url":"https://pith.science/pith/S6PZHZKJILYAR4VCVVNCUJUAZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6PZHZKJILYAR4VCVVNCUJUAZ2/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":"2026-08-03T18:51:51Z","links":{"resolver":"https://pith.science/pith/S6PZHZKJILYAR4VCVVNCUJUAZ2","bundle":"https://pith.science/pith/S6PZHZKJILYAR4VCVVNCUJUAZ2/bundle.json","state":"https://pith.science/pith/S6PZHZKJILYAR4VCVVNCUJUAZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6PZHZKJILYAR4VCVVNCUJUAZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S6PZHZKJILYAR4VCVVNCUJUAZ2","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":"4519d445edf69f43aa0e195cbb5335aea21d60b9adb7de13d813e851ff87dca8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T07:03:28Z","title_canon_sha256":"4d16577e2b99fa90afc48e22ae2e570911bc2621274cb41bb1ff108b2be2437c"},"schema_version":"1.0","source":{"id":"2406.03791","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03791","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03791v1","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03791","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"S6PZHZKJILYA","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"S6PZHZKJILYAR4VC","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"S6PZHZKJ","created_at":"2026-07-05T08:28:15Z"}],"graph_snapshots":[{"event_id":"sha256:14cd705b3a857d16e81a41529fb6e0602d944606eb9183d65fa793141ab55d50","target":"graph","created_at":"2026-07-05T08:28:15Z","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/2406.03791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of the time. Leveraging a new CUDA 12.4 feature, CUDA graph conditional nodes, we present an exact GPU-based implementation of greedy decoding for RNN-T models that eliminates this idle time. Our optimizations speed up a 1.1 billion parameter RNN-T model end-to-end by a factor of 2.5x. This technique can applied to the \"label looping\" alternative greedy decoding algorithm as well, achieving 1.7x and 1.4x end-to-end spe","authors_text":"Daniel Galvez, Hainan Xu, Tim Kaldewey, Vladimir Bataev","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T07:03:28Z","title":"Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03791","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":"sha256:59c4cd28aff0bd7528f9e7e4288b4e55f4e141c5b95f4adb617eed7fe8786d01","target":"record","created_at":"2026-07-05T08:28:15Z","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":"4519d445edf69f43aa0e195cbb5335aea21d60b9adb7de13d813e851ff87dca8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T07:03:28Z","title_canon_sha256":"4d16577e2b99fa90afc48e22ae2e570911bc2621274cb41bb1ff108b2be2437c"},"schema_version":"1.0","source":{"id":"2406.03791","kind":"arxiv","version":1}},"canonical_sha256":"979f93e54942f008f2a2ad5a2a2680cea42f56a837bf530ac07c4d5b191e18be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"979f93e54942f008f2a2ad5a2a2680cea42f56a837bf530ac07c4d5b191e18be","first_computed_at":"2026-07-05T08:28:15.961593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:15.961593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PL0/mEKC3J0LS5f9AwDkhcL9DtL/ilL24o8E2TmEEJ7K7Kzo+/p5RJKCgJmUnN/Zoro9TteLvOLrdszh6zJODg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:15.961971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03791","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59c4cd28aff0bd7528f9e7e4288b4e55f4e141c5b95f4adb617eed7fe8786d01","sha256:14cd705b3a857d16e81a41529fb6e0602d944606eb9183d65fa793141ab55d50"],"state_sha256":"87b24fb51899fe037f3740d3e9c3070a2decc9790354e1f4253c8119895bad60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/rbQ6W5/7X4t8ZtZILuljskfBOu7kK8E4IMuZaiUN6AsfElPMGyVIxfYdmTfgGZh70PxqAPhGXaC8WKtFmrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:51:51.613117Z","bundle_sha256":"ceca842f701a1bfc3c19d2d0f36f05069582348971b16747732460ef26a8b69d"}}