{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4QJLU63PNRULBCR62CENMQ7P6Y","short_pith_number":"pith:4QJLU63P","schema_version":"1.0","canonical_sha256":"e412ba7b6f6c68b08a3ed088d643eff608240bbe3b3b28043015fbbbe2911d84","source":{"kind":"arxiv","id":"2002.05150","version":1},"attestation_state":"computed","paper":{"title":"Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Julian Salazar, Phillip Keung, Vikas Bhardwaj, Wei Niu, Yichao Lu","submitted_at":"2020-02-12T18:53:56Z","abstract_excerpt":"We discuss the problem of echographic transcription in autoregressive sequence-to-sequence attentional architectures for automatic speech recognition, where a model produces very long sequences of repetitive outputs when presented with out-of-domain utterances. We decode audio from the British National Corpus with an attentional encoder-decoder model trained solely on the LibriSpeech corpus. We observe that there are many 5-second recordings that produce more than 500 characters of decoding output (i.e. more than 100 characters per second). A frame-synchronous hybrid (DNN-HMM) model trained on"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2002.05150","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-12T18:53:56Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"3e2660a076334273487f0629a9002887de37b2a647c2eef126253f468538a2b4","abstract_canon_sha256":"813652c32c0f21755c3f902b64ae2037ba1787f9e6fe37e6637eb84d5b8ae439"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:21.646207Z","signature_b64":"T9F5XweHzZrH1516wTzDCBhMCBxxWwTVXYOiLfezSxyRE1qRi9yujbzRhgc1zuOrdrM3+PvtImXGNm74KOvkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e412ba7b6f6c68b08a3ed088d643eff608240bbe3b3b28043015fbbbe2911d84","last_reissued_at":"2026-07-05T00:40:21.645796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:21.645796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Julian Salazar, Phillip Keung, Vikas Bhardwaj, Wei Niu, Yichao Lu","submitted_at":"2020-02-12T18:53:56Z","abstract_excerpt":"We discuss the problem of echographic transcription in autoregressive sequence-to-sequence attentional architectures for automatic speech recognition, where a model produces very long sequences of repetitive outputs when presented with out-of-domain utterances. We decode audio from the British National Corpus with an attentional encoder-decoder model trained solely on the LibriSpeech corpus. We observe that there are many 5-second recordings that produce more than 500 characters of decoding output (i.e. more than 100 characters per second). A frame-synchronous hybrid (DNN-HMM) model trained on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05150","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/2002.05150/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2002.05150","created_at":"2026-07-05T00:40:21.645856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05150v1","created_at":"2026-07-05T00:40:21.645856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05150","created_at":"2026-07-05T00:40:21.645856+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QJLU63PNRUL","created_at":"2026-07-05T00:40:21.645856+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QJLU63PNRULBCR6","created_at":"2026-07-05T00:40:21.645856+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QJLU63P","created_at":"2026-07-05T00:40:21.645856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y","json":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y.json","graph_json":"https://pith.science/api/pith-number/4QJLU63PNRULBCR62CENMQ7P6Y/graph.json","events_json":"https://pith.science/api/pith-number/4QJLU63PNRULBCR62CENMQ7P6Y/events.json","paper":"https://pith.science/paper/4QJLU63P"},"agent_actions":{"view_html":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y","download_json":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y.json","view_paper":"https://pith.science/paper/4QJLU63P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05150&json=true","fetch_graph":"https://pith.science/api/pith-number/4QJLU63PNRULBCR62CENMQ7P6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/4QJLU63PNRULBCR62CENMQ7P6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y/action/storage_attestation","attest_author":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y/action/author_attestation","sign_citation":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y/action/citation_signature","submit_replication":"https://pith.science/pith/4QJLU63PNRULBCR62CENMQ7P6Y/action/replication_record"}},"created_at":"2026-07-05T00:40:21.645856+00:00","updated_at":"2026-07-05T00:40:21.645856+00:00"}