{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AZNJIISYJM2TKPTIOTEL65VQWS","short_pith_number":"pith:AZNJIISY","schema_version":"1.0","canonical_sha256":"065a9422584b35353e6874c8bf76b0b481be7b772e6f9d70e493d3c170eb11bd","source":{"kind":"arxiv","id":"1902.10949","version":3},"attestation_state":"computed","paper":{"title":"Dynamic Multi-path Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ding Liang, Dixin Zheng, Jiaheng Liu, Junjie Yan, Shunfeng Zhou, Tian Su, Xiaolin Hu, Yichao Wu, Yingcheng Su, Yingxu Wang","submitted_at":"2019-02-28T08:48:18Z","abstract_excerpt":"Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resource-constrained applications. Existing methods usually choose to execute or skip an entire specific layer, which can only alter the depth of the network. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more path selection choices in terms of network width and depth during inference. The inference path of the network is determined by a controller, which takes into"},"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":"1902.10949","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-28T08:48:18Z","cross_cats_sorted":[],"title_canon_sha256":"3ca6b904e9bc4dd476d47f457a9fdfa2e3bd799a14a4561e6f3d18202919b030","abstract_canon_sha256":"c00c5b3cf48fa374f2511f3096ef41fd53020b0f2d457dea5f58d2779bcf6581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:14.547451Z","signature_b64":"A1Y/+ebKcTbqTGS/6YcKs3MQ3jaJ9m0FG3guPImnSIcKKyUXKZuIUsEtfl4FVp1mimh61FWWBXIT/bjjTVXNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"065a9422584b35353e6874c8bf76b0b481be7b772e6f9d70e493d3c170eb11bd","last_reissued_at":"2026-05-17T23:49:14.546609Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:14.546609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Multi-path Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ding Liang, Dixin Zheng, Jiaheng Liu, Junjie Yan, Shunfeng Zhou, Tian Su, Xiaolin Hu, Yichao Wu, Yingcheng Su, Yingxu Wang","submitted_at":"2019-02-28T08:48:18Z","abstract_excerpt":"Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resource-constrained applications. Existing methods usually choose to execute or skip an entire specific layer, which can only alter the depth of the network. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more path selection choices in terms of network width and depth during inference. The inference path of the network is determined by a controller, which takes into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10949","kind":"arxiv","version":3},"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":"1902.10949","created_at":"2026-05-17T23:49:14.546750+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10949v3","created_at":"2026-05-17T23:49:14.546750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10949","created_at":"2026-05-17T23:49:14.546750+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZNJIISYJM2T","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZNJIISYJM2TKPTI","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZNJIISY","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS","json":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS.json","graph_json":"https://pith.science/api/pith-number/AZNJIISYJM2TKPTIOTEL65VQWS/graph.json","events_json":"https://pith.science/api/pith-number/AZNJIISYJM2TKPTIOTEL65VQWS/events.json","paper":"https://pith.science/paper/AZNJIISY"},"agent_actions":{"view_html":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS","download_json":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS.json","view_paper":"https://pith.science/paper/AZNJIISY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10949&json=true","fetch_graph":"https://pith.science/api/pith-number/AZNJIISYJM2TKPTIOTEL65VQWS/graph.json","fetch_events":"https://pith.science/api/pith-number/AZNJIISYJM2TKPTIOTEL65VQWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS/action/storage_attestation","attest_author":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS/action/author_attestation","sign_citation":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS/action/citation_signature","submit_replication":"https://pith.science/pith/AZNJIISYJM2TKPTIOTEL65VQWS/action/replication_record"}},"created_at":"2026-05-17T23:49:14.546750+00:00","updated_at":"2026-05-17T23:49:14.546750+00:00"}