{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VKDAKPEAFFNKCOSIID5ASK7HDQ","short_pith_number":"pith:VKDAKPEA","schema_version":"1.0","canonical_sha256":"aa86053c80295aa13a4840fa092be71c015509f2f858b3e5cdec669fb3dbbf1a","source":{"kind":"arxiv","id":"1712.01996","version":1},"attestation_state":"computed","paper":{"title":"An analysis of incorporating an external language model into a sequence-to-sequence model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Anjuli Kannan, Patrick Nguyen, Rohit Prabhavalkar, Tara N. Sainath, Yonghui Wu, Zhifeng Chen","submitted_at":"2017-12-06T01:30:54Z","abstract_excerpt":"Attention-based sequence-to-sequence models for automatic speech recognition jointly train an acoustic model, language model, and alignment mechanism. Thus, the language model component is only trained on transcribed audio-text pairs. This leads to the use of shallow fusion with an external language model at inference time. Shallow fusion refers to log-linear interpolation with a separately trained language model at each step of the beam search. In this work, we investigate the behavior of shallow fusion across a range of conditions: different types of language models, different decoding units"},"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":"1712.01996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2017-12-06T01:30:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"f7455e0e3f516e5771e5fa6a21465a8cebee7a2ab9e374255610f257f662e233","abstract_canon_sha256":"2edf7391014872b484aed79262ccc471fbd62122a6b0fa3e1c61b18cf0cc4a83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:39.489384Z","signature_b64":"BfZz1IS0/0nK0c9Qdv2umx3BV0qkH2TkUzHWeqrMbZUwW7rtS8KEdehopK7Y+8cjGS7p0NvehJXwNZ8FW1EdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa86053c80295aa13a4840fa092be71c015509f2f858b3e5cdec669fb3dbbf1a","last_reissued_at":"2026-05-18T00:28:39.488733Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:39.488733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An analysis of incorporating an external language model into a sequence-to-sequence model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Anjuli Kannan, Patrick Nguyen, Rohit Prabhavalkar, Tara N. Sainath, Yonghui Wu, Zhifeng Chen","submitted_at":"2017-12-06T01:30:54Z","abstract_excerpt":"Attention-based sequence-to-sequence models for automatic speech recognition jointly train an acoustic model, language model, and alignment mechanism. Thus, the language model component is only trained on transcribed audio-text pairs. This leads to the use of shallow fusion with an external language model at inference time. Shallow fusion refers to log-linear interpolation with a separately trained language model at each step of the beam search. In this work, we investigate the behavior of shallow fusion across a range of conditions: different types of language models, different decoding units"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01996","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.01996","created_at":"2026-05-18T00:28:39.488829+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.01996v1","created_at":"2026-05-18T00:28:39.488829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01996","created_at":"2026-05-18T00:28:39.488829+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKDAKPEAFFNK","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKDAKPEAFFNKCOSI","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKDAKPEA","created_at":"2026-05-18T12:31:49.984773+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/VKDAKPEAFFNKCOSIID5ASK7HDQ","json":"https://pith.science/pith/VKDAKPEAFFNKCOSIID5ASK7HDQ.json","graph_json":"https://pith.science/api/pith-number/VKDAKPEAFFNKCOSIID5ASK7HDQ/graph.json","events_json":"https://pith.science/api/pith-number/VKDAKPEAFFNKCOSIID5ASK7HDQ/events.json","paper":"https://pith.science/paper/VKDAKPEA"},"agent_actions":{"view_html":"https://pith.science/pith/VKDAKPEAFFNKCOSIID5ASK7HDQ","download_json":"https://pith.science/pith/VKDAKPEAFFNKCOSIID5ASK7HDQ.json","view_paper":"https://pith.science/paper/VKDAKPEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.01996&json=true","fetch_graph":"https://pith.science/api/pith-number/VKDAKPEAFFNKCOSIID5ASK7HDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VKDAKPEAFFNKCOSIID5ASK7HDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKDAKPEAFFNKCOSIID5ASK7HDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKDAKPEAFFNKCOSIID5ASK7HDQ/action/storage_attestation","attest_author":"https://pith.science/pith/VKDAKPEAFFNKCOSIID5ASK7HDQ/action/author_attestation","sign_citation":"https://pith.science/pith/VKDAKPEAFFNKCOSIID5ASK7HDQ/action/citation_signature","submit_replication":"https://pith.science/pith/VKDAKPEAFFNKCOSIID5ASK7HDQ/action/replication_record"}},"created_at":"2026-05-18T00:28:39.488829+00:00","updated_at":"2026-05-18T00:28:39.488829+00:00"}