{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TQLHIKJPPN5ZGUBKOS4SDDRZ3Q","short_pith_number":"pith:TQLHIKJP","schema_version":"1.0","canonical_sha256":"9c1674292f7b7b93502a74b9218e39dc3c24f0577ac02990782790e99648a202","source":{"kind":"arxiv","id":"2105.03014","version":1},"attestation_state":"computed","paper":{"title":"BasisNet: Two-stage Model Synthesis for Efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Kovashka, Andrew Howard, Andrey Zhmoginov, Brendan Jou, Chun-Te Chu, Li Zhang, Mingda Zhang, Rebecca Hwa, Yukun Zhu","submitted_at":"2021-05-07T00:21:56Z","abstract_excerpt":"In this work, we present BasisNet which combines recent advancements in efficient neural network architectures, conditional computation, and early termination in a simple new form. Our approach incorporates a lightweight model to preview the input and generate input-dependent combination coefficients, which later controls the synthesis of a more accurate specialist model to make final prediction. The two-stage model synthesis strategy can be applied to any network architectures and both stages are jointly trained. We also show that proper training recipes are critical for increasing generaliza"},"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":"2105.03014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-07T00:21:56Z","cross_cats_sorted":[],"title_canon_sha256":"d5afe5468a6399fd96df8a42b74d4c5de48fce2851c4c6343eccc891f5ede6e4","abstract_canon_sha256":"4eb6bcf33eedb15fef1f94d62be0399a2b90a65b980e3a15f2f121383b007db4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:20.643964Z","signature_b64":"/ZWgu1n7kUJirmuwcywnOoGVDFjUOwbbiMpGkUdtUKCkwrccbYhwHbN71IaVobYFqhUqypgqyCrEGc+sdrjNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c1674292f7b7b93502a74b9218e39dc3c24f0577ac02990782790e99648a202","last_reissued_at":"2026-07-05T02:38:20.643447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:20.643447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BasisNet: Two-stage Model Synthesis for Efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Kovashka, Andrew Howard, Andrey Zhmoginov, Brendan Jou, Chun-Te Chu, Li Zhang, Mingda Zhang, Rebecca Hwa, Yukun Zhu","submitted_at":"2021-05-07T00:21:56Z","abstract_excerpt":"In this work, we present BasisNet which combines recent advancements in efficient neural network architectures, conditional computation, and early termination in a simple new form. Our approach incorporates a lightweight model to preview the input and generate input-dependent combination coefficients, which later controls the synthesis of a more accurate specialist model to make final prediction. The two-stage model synthesis strategy can be applied to any network architectures and both stages are jointly trained. We also show that proper training recipes are critical for increasing generaliza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03014","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/2105.03014/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":"2105.03014","created_at":"2026-07-05T02:38:20.643512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.03014v1","created_at":"2026-07-05T02:38:20.643512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03014","created_at":"2026-07-05T02:38:20.643512+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQLHIKJPPN5Z","created_at":"2026-07-05T02:38:20.643512+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQLHIKJPPN5ZGUBK","created_at":"2026-07-05T02:38:20.643512+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQLHIKJP","created_at":"2026-07-05T02:38:20.643512+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/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q","json":"https://pith.science/pith/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q.json","graph_json":"https://pith.science/api/pith-number/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/graph.json","events_json":"https://pith.science/api/pith-number/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/events.json","paper":"https://pith.science/paper/TQLHIKJP"},"agent_actions":{"view_html":"https://pith.science/pith/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q","download_json":"https://pith.science/pith/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q.json","view_paper":"https://pith.science/paper/TQLHIKJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.03014&json=true","fetch_graph":"https://pith.science/api/pith-number/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/action/storage_attestation","attest_author":"https://pith.science/pith/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/action/author_attestation","sign_citation":"https://pith.science/pith/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/action/citation_signature","submit_replication":"https://pith.science/pith/TQLHIKJPPN5ZGUBKOS4SDDRZ3Q/action/replication_record"}},"created_at":"2026-07-05T02:38:20.643512+00:00","updated_at":"2026-07-05T02:38:20.643512+00:00"}