{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FFR3VKHO4726A7L5ORR64KZROQ","short_pith_number":"pith:FFR3VKHO","schema_version":"1.0","canonical_sha256":"2963baa8eee7f5e07d7d7463ee2b31740df4f62cb3b726afcdcaf347d61da5b5","source":{"kind":"arxiv","id":"1611.05431","version":2},"attestation_state":"computed","paper":{"title":"Aggregated Residual Transformations for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiming He, Piotr Doll\\'ar, Ross Girshick, Saining Xie, Zhuowen Tu","submitted_at":"2016-11-16T20:34:42Z","abstract_excerpt":"We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call \"cardinality\" (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of ma"},"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":"1611.05431","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-16T20:34:42Z","cross_cats_sorted":[],"title_canon_sha256":"8979adc10a43d6cb7a667c0566b95ab6b76f14d744037ef1ac65ef7d14740403","abstract_canon_sha256":"bf32621214c318efda1a422a28177c8e23c9533c6aadd7a2f9e3da46940a689f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:38.972908Z","signature_b64":"s/rR1ZfXI7ZrXOleXy4bA5I2aQhEv/HDEL+sVIrVHun+PEgk+LO3eVCXW7bGExAlGjJK8zZhMoQXY3ujgnPJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2963baa8eee7f5e07d7d7463ee2b31740df4f62cb3b726afcdcaf347d61da5b5","last_reissued_at":"2026-05-18T00:46:38.972206Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:38.972206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aggregated Residual Transformations for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiming He, Piotr Doll\\'ar, Ross Girshick, Saining Xie, Zhuowen Tu","submitted_at":"2016-11-16T20:34:42Z","abstract_excerpt":"We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call \"cardinality\" (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05431","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":""},"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":"1611.05431","created_at":"2026-05-18T00:46:38.972331+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05431v2","created_at":"2026-05-18T00:46:38.972331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05431","created_at":"2026-05-18T00:46:38.972331+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFR3VKHO4726","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFR3VKHO4726A7L5","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFR3VKHO","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2305.07152","citing_title":"Intuitive Surgical SurgToolLoc and SurgVU Challenges Results: 2022-2025","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2512.18503","citing_title":"NASTaR: NovaSAR Automated Ship Target Recognition Dataset","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ","json":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ.json","graph_json":"https://pith.science/api/pith-number/FFR3VKHO4726A7L5ORR64KZROQ/graph.json","events_json":"https://pith.science/api/pith-number/FFR3VKHO4726A7L5ORR64KZROQ/events.json","paper":"https://pith.science/paper/FFR3VKHO"},"agent_actions":{"view_html":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ","download_json":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ.json","view_paper":"https://pith.science/paper/FFR3VKHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05431&json=true","fetch_graph":"https://pith.science/api/pith-number/FFR3VKHO4726A7L5ORR64KZROQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FFR3VKHO4726A7L5ORR64KZROQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ/action/storage_attestation","attest_author":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ/action/author_attestation","sign_citation":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ/action/citation_signature","submit_replication":"https://pith.science/pith/FFR3VKHO4726A7L5ORR64KZROQ/action/replication_record"}},"created_at":"2026-05-18T00:46:38.972331+00:00","updated_at":"2026-05-18T00:46:38.972331+00:00"}