{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:INJDJOVVZJOLDJKLEVYF2PRXEE","short_pith_number":"pith:INJDJOVV","schema_version":"1.0","canonical_sha256":"435234bab5ca5cb1a54b25705d3e37211b582df6b1146806368e80a0e7319564","source":{"kind":"arxiv","id":"2105.07085","version":2},"attestation_state":"computed","paper":{"title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Matias Mendieta, Minwoo Lee, Mubarak Shah, Pu Wang, Ravikumar Balakrishnan, Sijie Zhu, Tao Han, Taojiannan Yang","submitted_at":"2021-05-14T22:30:13Z","abstract_excerpt":"Most existing deep neural networks are static, which means they can only do inference at a fixed complexity. But the resource budget can vary substantially across different devices. Even on a single device, the affordable budget can change with different scenarios, and repeatedly training networks for each required budget would be incredibly expensive. Therefore, in this work, we propose a general method called MutualNet to train a single network that can run at a diverse set of resource constraints. Our method trains a cohort of model configurations with various network widths and input resol"},"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":"2105.07085","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-14T22:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"be73834ff3f4eb7d555a162597e8801794fdf8721fbe1035c8957e5f91576471","abstract_canon_sha256":"69e6d7e8c2577a018ecb21ac085b01cc3aad03cc44d0c81de7f3a6aea9354137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:29.409946Z","signature_b64":"HM4KWO7E6766rsDUeLn9RyKjtZ4IPZBi4BEf7dPBACATrZIzMqK50WlVdoy1/JCsdRFqK40n7RhCznX1iBnZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"435234bab5ca5cb1a54b25705d3e37211b582df6b1146806368e80a0e7319564","last_reissued_at":"2026-07-05T03:44:29.409569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:29.409569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Matias Mendieta, Minwoo Lee, Mubarak Shah, Pu Wang, Ravikumar Balakrishnan, Sijie Zhu, Tao Han, Taojiannan Yang","submitted_at":"2021-05-14T22:30:13Z","abstract_excerpt":"Most existing deep neural networks are static, which means they can only do inference at a fixed complexity. But the resource budget can vary substantially across different devices. Even on a single device, the affordable budget can change with different scenarios, and repeatedly training networks for each required budget would be incredibly expensive. Therefore, in this work, we propose a general method called MutualNet to train a single network that can run at a diverse set of resource constraints. Our method trains a cohort of model configurations with various network widths and input resol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07085","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/2105.07085/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":"2105.07085","created_at":"2026-07-05T03:44:29.409634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07085v2","created_at":"2026-07-05T03:44:29.409634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07085","created_at":"2026-07-05T03:44:29.409634+00:00"},{"alias_kind":"pith_short_12","alias_value":"INJDJOVVZJOL","created_at":"2026-07-05T03:44:29.409634+00:00"},{"alias_kind":"pith_short_16","alias_value":"INJDJOVVZJOLDJKL","created_at":"2026-07-05T03:44:29.409634+00:00"},{"alias_kind":"pith_short_8","alias_value":"INJDJOVV","created_at":"2026-07-05T03:44:29.409634+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/INJDJOVVZJOLDJKLEVYF2PRXEE","json":"https://pith.science/pith/INJDJOVVZJOLDJKLEVYF2PRXEE.json","graph_json":"https://pith.science/api/pith-number/INJDJOVVZJOLDJKLEVYF2PRXEE/graph.json","events_json":"https://pith.science/api/pith-number/INJDJOVVZJOLDJKLEVYF2PRXEE/events.json","paper":"https://pith.science/paper/INJDJOVV"},"agent_actions":{"view_html":"https://pith.science/pith/INJDJOVVZJOLDJKLEVYF2PRXEE","download_json":"https://pith.science/pith/INJDJOVVZJOLDJKLEVYF2PRXEE.json","view_paper":"https://pith.science/paper/INJDJOVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07085&json=true","fetch_graph":"https://pith.science/api/pith-number/INJDJOVVZJOLDJKLEVYF2PRXEE/graph.json","fetch_events":"https://pith.science/api/pith-number/INJDJOVVZJOLDJKLEVYF2PRXEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INJDJOVVZJOLDJKLEVYF2PRXEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INJDJOVVZJOLDJKLEVYF2PRXEE/action/storage_attestation","attest_author":"https://pith.science/pith/INJDJOVVZJOLDJKLEVYF2PRXEE/action/author_attestation","sign_citation":"https://pith.science/pith/INJDJOVVZJOLDJKLEVYF2PRXEE/action/citation_signature","submit_replication":"https://pith.science/pith/INJDJOVVZJOLDJKLEVYF2PRXEE/action/replication_record"}},"created_at":"2026-07-05T03:44:29.409634+00:00","updated_at":"2026-07-05T03:44:29.409634+00:00"}