{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EGYKG2RSMEQWCV57UWD2EPJODY","short_pith_number":"pith:EGYKG2RS","schema_version":"1.0","canonical_sha256":"21b0a36a3261216157bfa587a23d2e1e31d131aa255c5dc8198468e2e7cf6088","source":{"kind":"arxiv","id":"1909.12978","version":3},"attestation_state":"computed","paper":{"title":"MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Willis, Chen Chen, Mi Zhang, Shen Yan, Sijie Zhu, Taojiannan Yang","submitted_at":"2019-09-27T22:33:15Z","abstract_excerpt":"We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime. Our method trains a cohort of sub-networks with different widths using different input resolutions to mutually learn multi-scale representations for each sub-network. It achieves consistently better ImageNet top-1 accuracy over the state-of-the-art adaptive network US-Net under different computation constraints, and outperforms the best compound scaled MobileNet in EfficientNet by 1.5%. The superi"},"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":"1909.12978","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-27T22:33:15Z","cross_cats_sorted":[],"title_canon_sha256":"7039182f18c23f82be9574b502eeb9498270af791096e695d76bb74cd54efdd9","abstract_canon_sha256":"9af179631e382d8448f0c73e96fea48a7213e9dc191b532f5bc75697c2274477"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:52.813935Z","signature_b64":"IsKGs1qvj0a5KTKUFRmlIKkAaRoWLvKAOWCtseFzGVBDvvQ6C6Z9+nxwFbplwcY7xik/gX4NWzOvFWSTA5jNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21b0a36a3261216157bfa587a23d2e1e31d131aa255c5dc8198468e2e7cf6088","last_reissued_at":"2026-07-05T00:49:52.813522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:52.813522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Willis, Chen Chen, Mi Zhang, Shen Yan, Sijie Zhu, Taojiannan Yang","submitted_at":"2019-09-27T22:33:15Z","abstract_excerpt":"We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime. Our method trains a cohort of sub-networks with different widths using different input resolutions to mutually learn multi-scale representations for each sub-network. It achieves consistently better ImageNet top-1 accuracy over the state-of-the-art adaptive network US-Net under different computation constraints, and outperforms the best compound scaled MobileNet in EfficientNet by 1.5%. The superi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12978","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.12978/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":"1909.12978","created_at":"2026-07-05T00:49:52.813579+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12978v3","created_at":"2026-07-05T00:49:52.813579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12978","created_at":"2026-07-05T00:49:52.813579+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGYKG2RSMEQW","created_at":"2026-07-05T00:49:52.813579+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGYKG2RSMEQWCV57","created_at":"2026-07-05T00:49:52.813579+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGYKG2RS","created_at":"2026-07-05T00:49:52.813579+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/EGYKG2RSMEQWCV57UWD2EPJODY","json":"https://pith.science/pith/EGYKG2RSMEQWCV57UWD2EPJODY.json","graph_json":"https://pith.science/api/pith-number/EGYKG2RSMEQWCV57UWD2EPJODY/graph.json","events_json":"https://pith.science/api/pith-number/EGYKG2RSMEQWCV57UWD2EPJODY/events.json","paper":"https://pith.science/paper/EGYKG2RS"},"agent_actions":{"view_html":"https://pith.science/pith/EGYKG2RSMEQWCV57UWD2EPJODY","download_json":"https://pith.science/pith/EGYKG2RSMEQWCV57UWD2EPJODY.json","view_paper":"https://pith.science/paper/EGYKG2RS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12978&json=true","fetch_graph":"https://pith.science/api/pith-number/EGYKG2RSMEQWCV57UWD2EPJODY/graph.json","fetch_events":"https://pith.science/api/pith-number/EGYKG2RSMEQWCV57UWD2EPJODY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGYKG2RSMEQWCV57UWD2EPJODY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGYKG2RSMEQWCV57UWD2EPJODY/action/storage_attestation","attest_author":"https://pith.science/pith/EGYKG2RSMEQWCV57UWD2EPJODY/action/author_attestation","sign_citation":"https://pith.science/pith/EGYKG2RSMEQWCV57UWD2EPJODY/action/citation_signature","submit_replication":"https://pith.science/pith/EGYKG2RSMEQWCV57UWD2EPJODY/action/replication_record"}},"created_at":"2026-07-05T00:49:52.813579+00:00","updated_at":"2026-07-05T00:49:52.813579+00:00"}