{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FKKAEYU46DVMNQVZZBZBHIFZQJ","short_pith_number":"pith:FKKAEYU4","schema_version":"1.0","canonical_sha256":"2a9402629cf0eac6c2b9c87213a0b9826218ddcb2a2da57ab40d5e624409d021","source":{"kind":"arxiv","id":"2106.09216","version":1},"attestation_state":"computed","paper":{"title":"Layer Pruning on Demand with Intermediate CTC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jaesong Lee, Jingu Kang, Shinji Watanabe","submitted_at":"2021-06-17T02:40:18Z","abstract_excerpt":"Deploying an end-to-end automatic speech recognition (ASR) model on mobile/embedded devices is a challenging task, since the device computational power and energy consumption requirements are dynamically changed in practice. To overcome the issue, we present a training and pruning method for ASR based on the connectionist temporal classification (CTC) which allows reduction of model depth at run-time without any extra fine-tuning. To achieve the goal, we adopt two regularization methods, intermediate CTC and stochastic depth, to train a model whose performance does not degrade much after pruni"},"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":"2106.09216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-17T02:40:18Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"c16ed0f581c7963b27ca15d0a86d468fdf6807e70b850012d7fddc5219494498","abstract_canon_sha256":"b280b48c664e869aab7d579fe92b01fed8235620a967ca6167a680dc731eb56a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:13.568276Z","signature_b64":"ezxji6XsprnVHbywacr991LzyYFXT76riZ7yvPy6Qizjpdi+Ib4/Mxc773MYCSaq2rYXyBEvbVM99in0tgqPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a9402629cf0eac6c2b9c87213a0b9826218ddcb2a2da57ab40d5e624409d021","last_reissued_at":"2026-07-05T02:50:13.567923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:13.567923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer Pruning on Demand with Intermediate CTC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jaesong Lee, Jingu Kang, Shinji Watanabe","submitted_at":"2021-06-17T02:40:18Z","abstract_excerpt":"Deploying an end-to-end automatic speech recognition (ASR) model on mobile/embedded devices is a challenging task, since the device computational power and energy consumption requirements are dynamically changed in practice. To overcome the issue, we present a training and pruning method for ASR based on the connectionist temporal classification (CTC) which allows reduction of model depth at run-time without any extra fine-tuning. To achieve the goal, we adopt two regularization methods, intermediate CTC and stochastic depth, to train a model whose performance does not degrade much after pruni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09216","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/2106.09216/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":"2106.09216","created_at":"2026-07-05T02:50:13.567988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09216v1","created_at":"2026-07-05T02:50:13.567988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09216","created_at":"2026-07-05T02:50:13.567988+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKKAEYU46DVM","created_at":"2026-07-05T02:50:13.567988+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKKAEYU46DVMNQVZ","created_at":"2026-07-05T02:50:13.567988+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKKAEYU4","created_at":"2026-07-05T02:50:13.567988+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/FKKAEYU46DVMNQVZZBZBHIFZQJ","json":"https://pith.science/pith/FKKAEYU46DVMNQVZZBZBHIFZQJ.json","graph_json":"https://pith.science/api/pith-number/FKKAEYU46DVMNQVZZBZBHIFZQJ/graph.json","events_json":"https://pith.science/api/pith-number/FKKAEYU46DVMNQVZZBZBHIFZQJ/events.json","paper":"https://pith.science/paper/FKKAEYU4"},"agent_actions":{"view_html":"https://pith.science/pith/FKKAEYU46DVMNQVZZBZBHIFZQJ","download_json":"https://pith.science/pith/FKKAEYU46DVMNQVZZBZBHIFZQJ.json","view_paper":"https://pith.science/paper/FKKAEYU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09216&json=true","fetch_graph":"https://pith.science/api/pith-number/FKKAEYU46DVMNQVZZBZBHIFZQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FKKAEYU46DVMNQVZZBZBHIFZQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKKAEYU46DVMNQVZZBZBHIFZQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKKAEYU46DVMNQVZZBZBHIFZQJ/action/storage_attestation","attest_author":"https://pith.science/pith/FKKAEYU46DVMNQVZZBZBHIFZQJ/action/author_attestation","sign_citation":"https://pith.science/pith/FKKAEYU46DVMNQVZZBZBHIFZQJ/action/citation_signature","submit_replication":"https://pith.science/pith/FKKAEYU46DVMNQVZZBZBHIFZQJ/action/replication_record"}},"created_at":"2026-07-05T02:50:13.567988+00:00","updated_at":"2026-07-05T02:50:13.567988+00:00"}