{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BER64NRPK5NQRVPG62JM5LL5KP","short_pith_number":"pith:BER64NRP","schema_version":"1.0","canonical_sha256":"0923ee362f575b08d5e6f692cead7d53cece2c8b79c94efabea3228bbad9408c","source":{"kind":"arxiv","id":"2104.09379","version":2},"attestation_state":"computed","paper":{"title":"BM-NAS: Bilevel Multimodal Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Siyu Huang, Xiang Zhang, Yihang Yin","submitted_at":"2021-04-19T15:09:49Z","abstract_excerpt":"Deep neural networks (DNNs) have shown superior performances on various multimodal learning problems. However, it often requires huge efforts to adapt DNNs to individual multimodal tasks by manually engineering unimodal features and designing multimodal feature fusion strategies. This paper proposes Bilevel Multimodal Neural Architecture Search (BM-NAS) framework, which makes the architecture of multimodal fusion models fully searchable via a bilevel searching scheme. At the upper level, BM-NAS selects the inter/intra-modal feature pairs from the pretrained unimodal backbones. At the lower lev"},"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":"2104.09379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-19T15:09:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7028f1a14ed2a7679b928fbceb5f73a0916949ad4545be73dd402f98348a1fe1","abstract_canon_sha256":"30b5ad00a818aa403640ad8f8cc2e830bf088a5478a708bc936812d9fbb03712"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:53.146495Z","signature_b64":"l2tunPZEa1bPaSrO5YJzWWKBW3pkw3j6+C+gB+r7AATWVtYGBQzo4QzLloKl3anhw16lvAwK5LYLjoBvjnglDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0923ee362f575b08d5e6f692cead7d53cece2c8b79c94efabea3228bbad9408c","last_reissued_at":"2026-07-05T03:44:53.146001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:53.146001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BM-NAS: Bilevel Multimodal Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Siyu Huang, Xiang Zhang, Yihang Yin","submitted_at":"2021-04-19T15:09:49Z","abstract_excerpt":"Deep neural networks (DNNs) have shown superior performances on various multimodal learning problems. However, it often requires huge efforts to adapt DNNs to individual multimodal tasks by manually engineering unimodal features and designing multimodal feature fusion strategies. This paper proposes Bilevel Multimodal Neural Architecture Search (BM-NAS) framework, which makes the architecture of multimodal fusion models fully searchable via a bilevel searching scheme. At the upper level, BM-NAS selects the inter/intra-modal feature pairs from the pretrained unimodal backbones. At the lower lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09379","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/2104.09379/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":"2104.09379","created_at":"2026-07-05T03:44:53.146060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.09379v2","created_at":"2026-07-05T03:44:53.146060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09379","created_at":"2026-07-05T03:44:53.146060+00:00"},{"alias_kind":"pith_short_12","alias_value":"BER64NRPK5NQ","created_at":"2026-07-05T03:44:53.146060+00:00"},{"alias_kind":"pith_short_16","alias_value":"BER64NRPK5NQRVPG","created_at":"2026-07-05T03:44:53.146060+00:00"},{"alias_kind":"pith_short_8","alias_value":"BER64NRP","created_at":"2026-07-05T03:44:53.146060+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/BER64NRPK5NQRVPG62JM5LL5KP","json":"https://pith.science/pith/BER64NRPK5NQRVPG62JM5LL5KP.json","graph_json":"https://pith.science/api/pith-number/BER64NRPK5NQRVPG62JM5LL5KP/graph.json","events_json":"https://pith.science/api/pith-number/BER64NRPK5NQRVPG62JM5LL5KP/events.json","paper":"https://pith.science/paper/BER64NRP"},"agent_actions":{"view_html":"https://pith.science/pith/BER64NRPK5NQRVPG62JM5LL5KP","download_json":"https://pith.science/pith/BER64NRPK5NQRVPG62JM5LL5KP.json","view_paper":"https://pith.science/paper/BER64NRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.09379&json=true","fetch_graph":"https://pith.science/api/pith-number/BER64NRPK5NQRVPG62JM5LL5KP/graph.json","fetch_events":"https://pith.science/api/pith-number/BER64NRPK5NQRVPG62JM5LL5KP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BER64NRPK5NQRVPG62JM5LL5KP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BER64NRPK5NQRVPG62JM5LL5KP/action/storage_attestation","attest_author":"https://pith.science/pith/BER64NRPK5NQRVPG62JM5LL5KP/action/author_attestation","sign_citation":"https://pith.science/pith/BER64NRPK5NQRVPG62JM5LL5KP/action/citation_signature","submit_replication":"https://pith.science/pith/BER64NRPK5NQRVPG62JM5LL5KP/action/replication_record"}},"created_at":"2026-07-05T03:44:53.146060+00:00","updated_at":"2026-07-05T03:44:53.146060+00:00"}