{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:PGNWK44ZCIOL2S3EVJ7A7UFO5Y","short_pith_number":"pith:PGNWK44Z","canonical_record":{"source":{"id":"1408.2873","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-12T22:40:21Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e1c8dceeffb640e49ccad790e80c02e245fb33418d517447014f6a88d428bf20","abstract_canon_sha256":"58f1e1b0cecab29a92a1831bb99f8c0e2e24900aad9026d4ade473a2d99c6d78"},"schema_version":"1.0"},"canonical_sha256":"799b657399121cbd4b64aa7e0fd0aeee36c66dbf06773b4725225a70d0b7d0c9","source":{"kind":"arxiv","id":"1408.2873","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1408.2873","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"1408.2873v2","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.2873","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"PGNWK44ZCIOL","created_at":"2026-05-18T12:28:43Z"},{"alias_kind":"pith_short_16","alias_value":"PGNWK44ZCIOL2S3E","created_at":"2026-05-18T12:28:43Z"},{"alias_kind":"pith_short_8","alias_value":"PGNWK44Z","created_at":"2026-05-18T12:28:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:PGNWK44ZCIOL2S3EVJ7A7UFO5Y","target":"record","payload":{"canonical_record":{"source":{"id":"1408.2873","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-12T22:40:21Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e1c8dceeffb640e49ccad790e80c02e245fb33418d517447014f6a88d428bf20","abstract_canon_sha256":"58f1e1b0cecab29a92a1831bb99f8c0e2e24900aad9026d4ade473a2d99c6d78"},"schema_version":"1.0"},"canonical_sha256":"799b657399121cbd4b64aa7e0fd0aeee36c66dbf06773b4725225a70d0b7d0c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:59.569461Z","signature_b64":"ndyB2Smyc+Mu8s2F8KIsjHGesPVE2UgjqCr7bxvnSB0joCbwUs+QA4nHlONnBItAl/O7i4x+OkMcTqBMWwPGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"799b657399121cbd4b64aa7e0fd0aeee36c66dbf06773b4725225a70d0b7d0c9","last_reissued_at":"2026-05-18T02:31:59.568767Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:59.568767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1408.2873","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":"2026-05-18T02:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/zjh4lFfMgDWXL4nluxHNjdRkEEEZDyXejT5OOg4SdWncSTPwTNui7iQBl9cytKTSaPQB4z46dFsvps7w10xDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:21:59.116498Z"},"content_sha256":"51988b5ea2a7671b79b38054a8497bbb8423cc11b265944d6430b5f920e6802e","schema_version":"1.0","event_id":"sha256:51988b5ea2a7671b79b38054a8497bbb8423cc11b265944d6430b5f920e6802e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:PGNWK44ZCIOL2S3EVJ7A7UFO5Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Andrew L. Maas, Andrew Y. Ng, Awni Y. Hannun, Daniel Jurafsky","submitted_at":"2014-08-12T22:40:21Z","abstract_excerpt":"We present a method to perform first-pass large vocabulary continuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace in HMM-based speech recognition systems, but building such systems is a complex, domain-specific task. Recent work demonstrated the feasibility of discarding the HMM sequence modeling framework by directly predicting transcript text from audio. This paper extends this approach in two ways. First, we demonstrate that a straightforward recurrent neural network architecture can achieve a high level of accur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.2873","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":""},"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":"2026-05-18T02:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"088I7JibTcH9bFu+e66o3AnL4dfiP2AXkOJDphgs82NreGgUjk+qDsk/DOtw/5jCnl7J6i2Lfj6wRbDSe4foBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:21:59.116895Z"},"content_sha256":"1688a00978c44ecb455e383663f01da280c6bf9571a3399a8a2450c1e93cf0e9","schema_version":"1.0","event_id":"sha256:1688a00978c44ecb455e383663f01da280c6bf9571a3399a8a2450c1e93cf0e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PGNWK44ZCIOL2S3EVJ7A7UFO5Y/bundle.json","state_url":"https://pith.science/pith/PGNWK44ZCIOL2S3EVJ7A7UFO5Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PGNWK44ZCIOL2S3EVJ7A7UFO5Y/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":"2026-06-01T06:21:59Z","links":{"resolver":"https://pith.science/pith/PGNWK44ZCIOL2S3EVJ7A7UFO5Y","bundle":"https://pith.science/pith/PGNWK44ZCIOL2S3EVJ7A7UFO5Y/bundle.json","state":"https://pith.science/pith/PGNWK44ZCIOL2S3EVJ7A7UFO5Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PGNWK44ZCIOL2S3EVJ7A7UFO5Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:PGNWK44ZCIOL2S3EVJ7A7UFO5Y","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":"58f1e1b0cecab29a92a1831bb99f8c0e2e24900aad9026d4ade473a2d99c6d78","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-12T22:40:21Z","title_canon_sha256":"e1c8dceeffb640e49ccad790e80c02e245fb33418d517447014f6a88d428bf20"},"schema_version":"1.0","source":{"id":"1408.2873","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1408.2873","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"1408.2873v2","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.2873","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"PGNWK44ZCIOL","created_at":"2026-05-18T12:28:43Z"},{"alias_kind":"pith_short_16","alias_value":"PGNWK44ZCIOL2S3E","created_at":"2026-05-18T12:28:43Z"},{"alias_kind":"pith_short_8","alias_value":"PGNWK44Z","created_at":"2026-05-18T12:28:43Z"}],"graph_snapshots":[{"event_id":"sha256:1688a00978c44ecb455e383663f01da280c6bf9571a3399a8a2450c1e93cf0e9","target":"graph","created_at":"2026-05-18T02:31:59Z","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"},"paper":{"abstract_excerpt":"We present a method to perform first-pass large vocabulary continuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace in HMM-based speech recognition systems, but building such systems is a complex, domain-specific task. Recent work demonstrated the feasibility of discarding the HMM sequence modeling framework by directly predicting transcript text from audio. This paper extends this approach in two ways. First, we demonstrate that a straightforward recurrent neural network architecture can achieve a high level of accur","authors_text":"Andrew L. Maas, Andrew Y. Ng, Awni Y. Hannun, Daniel Jurafsky","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-12T22:40:21Z","title":"First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.2873","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":"sha256:51988b5ea2a7671b79b38054a8497bbb8423cc11b265944d6430b5f920e6802e","target":"record","created_at":"2026-05-18T02:31:59Z","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":"58f1e1b0cecab29a92a1831bb99f8c0e2e24900aad9026d4ade473a2d99c6d78","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-12T22:40:21Z","title_canon_sha256":"e1c8dceeffb640e49ccad790e80c02e245fb33418d517447014f6a88d428bf20"},"schema_version":"1.0","source":{"id":"1408.2873","kind":"arxiv","version":2}},"canonical_sha256":"799b657399121cbd4b64aa7e0fd0aeee36c66dbf06773b4725225a70d0b7d0c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"799b657399121cbd4b64aa7e0fd0aeee36c66dbf06773b4725225a70d0b7d0c9","first_computed_at":"2026-05-18T02:31:59.568767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:31:59.568767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ndyB2Smyc+Mu8s2F8KIsjHGesPVE2UgjqCr7bxvnSB0joCbwUs+QA4nHlONnBItAl/O7i4x+OkMcTqBMWwPGAg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:31:59.569461Z","signed_message":"canonical_sha256_bytes"},"source_id":"1408.2873","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51988b5ea2a7671b79b38054a8497bbb8423cc11b265944d6430b5f920e6802e","sha256:1688a00978c44ecb455e383663f01da280c6bf9571a3399a8a2450c1e93cf0e9"],"state_sha256":"d8bc1de00b72691c35090002f78d82e6f3753aee3e6816c35ed330518d382418"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C4lrqb1JarrnHKPt4es5Jzpmi2Aa37jBA8J+ewQRQuNcARheMSrVjL8/4rE169kdMwQX3cI2tCwkvf8Y0M/xDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:21:59.118981Z","bundle_sha256":"34f66d8bbb6f757d0dbd1c9c30f4a9d420e76104bfd7f055707f9f38b5fae40b"}}