{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TWI57X7FGL7YJYCBEIXQVFQKLZ","short_pith_number":"pith:TWI57X7F","schema_version":"1.0","canonical_sha256":"9d91dfdfe532ff84e041222f0a960a5e5aefc3f8913c7f67525c515fdd4ef100","source":{"kind":"arxiv","id":"1812.11928","version":2},"attestation_state":"computed","paper":{"title":"Advancing Acoustic-to-Word CTC Model with Attention and Mixed-Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Das, Guoli Ye, Jinyu Li, Rui Zhao, Yifan Gong","submitted_at":"2018-12-31T18:10:42Z","abstract_excerpt":"The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issues exist in the system: first, the current output of the CTC model relies on the current input and does not account for context weighted inputs. This is the hard alignment issue. Second, the word-based CTC model suffers from the out-of-vocabulary (OOV) issue. This means it can model only frequently occurring words while tagging the remaining words as OOV. Hence, such a model is limited in its capacity in recognizing o"},"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":"1812.11928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-31T18:10:42Z","cross_cats_sorted":[],"title_canon_sha256":"d15c573dedf39b0eff976056708eaa0344b705d190095118b5a0fb12b107d0f6","abstract_canon_sha256":"484f35c3700e6f1a3a83079d76ee0418f91e0a19cc81cee351d56b046f796e64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:24.820296Z","signature_b64":"usasLT9N7oRcfhGYlDAKy/qKFAru5U3us5yz/KVmNkTdnb5Aw10b79xM8Pkj0WSgw2D7OkPAXu975y2iQivaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d91dfdfe532ff84e041222f0a960a5e5aefc3f8913c7f67525c515fdd4ef100","last_reissued_at":"2026-07-05T00:02:24.819875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:24.819875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Acoustic-to-Word CTC Model with Attention and Mixed-Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Das, Guoli Ye, Jinyu Li, Rui Zhao, Yifan Gong","submitted_at":"2018-12-31T18:10:42Z","abstract_excerpt":"The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issues exist in the system: first, the current output of the CTC model relies on the current input and does not account for context weighted inputs. This is the hard alignment issue. Second, the word-based CTC model suffers from the out-of-vocabulary (OOV) issue. This means it can model only frequently occurring words while tagging the remaining words as OOV. Hence, such a model is limited in its capacity in recognizing o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11928","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1812.11928/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":"1812.11928","created_at":"2026-07-05T00:02:24.819932+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11928v2","created_at":"2026-07-05T00:02:24.819932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11928","created_at":"2026-07-05T00:02:24.819932+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWI57X7FGL7Y","created_at":"2026-07-05T00:02:24.819932+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWI57X7FGL7YJYCB","created_at":"2026-07-05T00:02:24.819932+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWI57X7F","created_at":"2026-07-05T00:02:24.819932+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/TWI57X7FGL7YJYCBEIXQVFQKLZ","json":"https://pith.science/pith/TWI57X7FGL7YJYCBEIXQVFQKLZ.json","graph_json":"https://pith.science/api/pith-number/TWI57X7FGL7YJYCBEIXQVFQKLZ/graph.json","events_json":"https://pith.science/api/pith-number/TWI57X7FGL7YJYCBEIXQVFQKLZ/events.json","paper":"https://pith.science/paper/TWI57X7F"},"agent_actions":{"view_html":"https://pith.science/pith/TWI57X7FGL7YJYCBEIXQVFQKLZ","download_json":"https://pith.science/pith/TWI57X7FGL7YJYCBEIXQVFQKLZ.json","view_paper":"https://pith.science/paper/TWI57X7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11928&json=true","fetch_graph":"https://pith.science/api/pith-number/TWI57X7FGL7YJYCBEIXQVFQKLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TWI57X7FGL7YJYCBEIXQVFQKLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWI57X7FGL7YJYCBEIXQVFQKLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWI57X7FGL7YJYCBEIXQVFQKLZ/action/storage_attestation","attest_author":"https://pith.science/pith/TWI57X7FGL7YJYCBEIXQVFQKLZ/action/author_attestation","sign_citation":"https://pith.science/pith/TWI57X7FGL7YJYCBEIXQVFQKLZ/action/citation_signature","submit_replication":"https://pith.science/pith/TWI57X7FGL7YJYCBEIXQVFQKLZ/action/replication_record"}},"created_at":"2026-07-05T00:02:24.819932+00:00","updated_at":"2026-07-05T00:02:24.819932+00:00"}