{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Q4WJ6F674EOMK6K7L7UJQ4UOO3","short_pith_number":"pith:Q4WJ6F67","canonical_record":{"source":{"id":"1703.07754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T17:17:16Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"9453d26caa4780117c870f3f3e99cfbab9aabb57b4341ac02453df234fcc5656","abstract_canon_sha256":"6144ef3dbfb798b3a8921247f7c98415d95a207f902677f773cc7761c4f5ec4e"},"schema_version":"1.0"},"canonical_sha256":"872c9f17dfe11cc5795f5fe898728e76ec910b514b58b4c669e62098934f7b43","source":{"kind":"arxiv","id":"1703.07754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07754","created_at":"2026-05-18T00:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07754v1","created_at":"2026-05-18T00:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07754","created_at":"2026-05-18T00:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"Q4WJ6F674EOM","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q4WJ6F674EOMK6K7","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q4WJ6F67","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Q4WJ6F674EOMK6K7L7UJQ4UOO3","target":"record","payload":{"canonical_record":{"source":{"id":"1703.07754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T17:17:16Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"9453d26caa4780117c870f3f3e99cfbab9aabb57b4341ac02453df234fcc5656","abstract_canon_sha256":"6144ef3dbfb798b3a8921247f7c98415d95a207f902677f773cc7761c4f5ec4e"},"schema_version":"1.0"},"canonical_sha256":"872c9f17dfe11cc5795f5fe898728e76ec910b514b58b4c669e62098934f7b43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:06.225177Z","signature_b64":"KNot+8h4rU3IbbUVG4r7pFw84diHX3nXfb6vymHwIRfiJvYS8caRGfMm4X7fwykkADfuyhP5rBkwro5nHdMqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"872c9f17dfe11cc5795f5fe898728e76ec910b514b58b4c669e62098934f7b43","last_reissued_at":"2026-05-18T00:48:06.224655Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:06.224655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.07754","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":"2026-05-18T00:48:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWrMgrwcLJSHCkL17QQW6GOk2o4Xyp+aHcI5ljCayemudNC36fOy/bjl//avpMGle4JtfDT2v6IlooUolebuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:49:29.300477Z"},"content_sha256":"7724a9711ae0e6f4dfe72edd85be2172bf60954db307c08780fc26aada70c485","schema_version":"1.0","event_id":"sha256:7724a9711ae0e6f4dfe72edd85be2172bf60954db307c08780fc26aada70c485"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Q4WJ6F674EOMK6K7L7UJQ4UOO3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Direct Acoustics-to-Word Models for English Conversational Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Bhuvana Ramabhadran, David Nahamoo, George Saon, Kartik Audhkhasi, Michael Picheny","submitted_at":"2017-03-22T17:17:16Z","abstract_excerpt":"Recent work on end-to-end automatic speech recognition (ASR) has shown that the connectionist temporal classification (CTC) loss can be used to convert acoustics to phone or character sequences. Such systems are used with a dictionary and separately-trained Language Model (LM) to produce word sequences. However, they are not truly end-to-end in the sense of mapping acoustics directly to words without an intermediate phone representation. In this paper, we present the first results employing direct acoustics-to-word CTC models on two well-known public benchmark tasks: Switchboard and CallHome. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07754","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":""},"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":"2026-05-18T00:48:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VRBY13A05uUP9s/wBlYCKieldCoauRijdJc76uN5VhIfms+iB9OmQ+HKkpuWfjaWom88SYMmiowzXmoobBrIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:49:29.300835Z"},"content_sha256":"37aed2c9adc1e25cdeb8e502aad56fcf48bf79d8264a0116dfa09a5494b778d1","schema_version":"1.0","event_id":"sha256:37aed2c9adc1e25cdeb8e502aad56fcf48bf79d8264a0116dfa09a5494b778d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4WJ6F674EOMK6K7L7UJQ4UOO3/bundle.json","state_url":"https://pith.science/pith/Q4WJ6F674EOMK6K7L7UJQ4UOO3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4WJ6F674EOMK6K7L7UJQ4UOO3/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":"2026-05-31T18:49:29Z","links":{"resolver":"https://pith.science/pith/Q4WJ6F674EOMK6K7L7UJQ4UOO3","bundle":"https://pith.science/pith/Q4WJ6F674EOMK6K7L7UJQ4UOO3/bundle.json","state":"https://pith.science/pith/Q4WJ6F674EOMK6K7L7UJQ4UOO3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4WJ6F674EOMK6K7L7UJQ4UOO3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Q4WJ6F674EOMK6K7L7UJQ4UOO3","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":"6144ef3dbfb798b3a8921247f7c98415d95a207f902677f773cc7761c4f5ec4e","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T17:17:16Z","title_canon_sha256":"9453d26caa4780117c870f3f3e99cfbab9aabb57b4341ac02453df234fcc5656"},"schema_version":"1.0","source":{"id":"1703.07754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07754","created_at":"2026-05-18T00:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07754v1","created_at":"2026-05-18T00:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07754","created_at":"2026-05-18T00:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"Q4WJ6F674EOM","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q4WJ6F674EOMK6K7","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q4WJ6F67","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:37aed2c9adc1e25cdeb8e502aad56fcf48bf79d8264a0116dfa09a5494b778d1","target":"graph","created_at":"2026-05-18T00:48:06Z","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":"Recent work on end-to-end automatic speech recognition (ASR) has shown that the connectionist temporal classification (CTC) loss can be used to convert acoustics to phone or character sequences. Such systems are used with a dictionary and separately-trained Language Model (LM) to produce word sequences. However, they are not truly end-to-end in the sense of mapping acoustics directly to words without an intermediate phone representation. In this paper, we present the first results employing direct acoustics-to-word CTC models on two well-known public benchmark tasks: Switchboard and CallHome. ","authors_text":"Bhuvana Ramabhadran, David Nahamoo, George Saon, Kartik Audhkhasi, Michael Picheny","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T17:17:16Z","title":"Direct Acoustics-to-Word Models for English Conversational Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07754","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":"sha256:7724a9711ae0e6f4dfe72edd85be2172bf60954db307c08780fc26aada70c485","target":"record","created_at":"2026-05-18T00:48:06Z","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":"6144ef3dbfb798b3a8921247f7c98415d95a207f902677f773cc7761c4f5ec4e","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T17:17:16Z","title_canon_sha256":"9453d26caa4780117c870f3f3e99cfbab9aabb57b4341ac02453df234fcc5656"},"schema_version":"1.0","source":{"id":"1703.07754","kind":"arxiv","version":1}},"canonical_sha256":"872c9f17dfe11cc5795f5fe898728e76ec910b514b58b4c669e62098934f7b43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"872c9f17dfe11cc5795f5fe898728e76ec910b514b58b4c669e62098934f7b43","first_computed_at":"2026-05-18T00:48:06.224655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:06.224655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KNot+8h4rU3IbbUVG4r7pFw84diHX3nXfb6vymHwIRfiJvYS8caRGfMm4X7fwykkADfuyhP5rBkwro5nHdMqAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:06.225177Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.07754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7724a9711ae0e6f4dfe72edd85be2172bf60954db307c08780fc26aada70c485","sha256:37aed2c9adc1e25cdeb8e502aad56fcf48bf79d8264a0116dfa09a5494b778d1"],"state_sha256":"bff68cef34fa981adb4743ea256e9c78d12d39babcabbaa42335ef2460bd9e49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sm04HcB2hkio+xAfr4rlD7F+cbSzJ76lS6Ok7p8ka0CvNaB4MAy7cjdZAODQowzrU/4Wb/DOPgDevAPtNXZkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:49:29.302950Z","bundle_sha256":"a8bdbe2a7f0e06b49e4d0260a21d8fcaa2b9e4dc5bbebabba9d47de27a75bf38"}}