{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QIZQZXOR42WEVMXIG64KDXVXOR","short_pith_number":"pith:QIZQZXOR","schema_version":"1.0","canonical_sha256":"82330cddd1e6ac4ab2e837b8a1deb774575d2db0f794ecd19c70df52338b64fe","source":{"kind":"arxiv","id":"1709.09582","version":2},"attestation_state":"computed","paper":{"title":"Connectivity Learning in Multi-Branch Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Karim Ahmed, Lorenzo Torresani","submitted_at":"2017-09-27T15:34:21Z","abstract_excerpt":"While much of the work in the design of convolutional networks over the last five years has revolved around the empirical investigation of the importance of depth, filter sizes, and number of feature channels, recent studies have shown that branching, i.e., splitting the computation along parallel but distinct threads and then aggregating their outputs, represents a new promising dimension for significant improvements in performance. To combat the complexity of design choices in multi-branch architectures, prior work has adopted simple strategies, such as a fixed branching factor, the same inp"},"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":"1709.09582","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-27T15:34:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2008223af87d834057cef337a7b2315f910bcb7bea8a3baa725c47abc12def3a","abstract_canon_sha256":"975e525d36c0c902e2f93f4275e98d5c753e8ae05a823848815182dff9b534e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:35.042909Z","signature_b64":"1a3+SyAQOHfz2yERPhGqT4rarsYtc3qDzdB6kT15p2Z5+7pakP6SpQpaQmX8LHzTniSx1drUFTCOVhDb1pLaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82330cddd1e6ac4ab2e837b8a1deb774575d2db0f794ecd19c70df52338b64fe","last_reissued_at":"2026-05-18T00:28:35.042195Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:35.042195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Connectivity Learning in Multi-Branch Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Karim Ahmed, Lorenzo Torresani","submitted_at":"2017-09-27T15:34:21Z","abstract_excerpt":"While much of the work in the design of convolutional networks over the last five years has revolved around the empirical investigation of the importance of depth, filter sizes, and number of feature channels, recent studies have shown that branching, i.e., splitting the computation along parallel but distinct threads and then aggregating their outputs, represents a new promising dimension for significant improvements in performance. To combat the complexity of design choices in multi-branch architectures, prior work has adopted simple strategies, such as a fixed branching factor, the same inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.09582","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":"1709.09582","created_at":"2026-05-18T00:28:35.042301+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.09582v2","created_at":"2026-05-18T00:28:35.042301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09582","created_at":"2026-05-18T00:28:35.042301+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIZQZXOR42WE","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIZQZXOR42WEVMXI","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIZQZXOR","created_at":"2026-05-18T12:31:39.905425+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/QIZQZXOR42WEVMXIG64KDXVXOR","json":"https://pith.science/pith/QIZQZXOR42WEVMXIG64KDXVXOR.json","graph_json":"https://pith.science/api/pith-number/QIZQZXOR42WEVMXIG64KDXVXOR/graph.json","events_json":"https://pith.science/api/pith-number/QIZQZXOR42WEVMXIG64KDXVXOR/events.json","paper":"https://pith.science/paper/QIZQZXOR"},"agent_actions":{"view_html":"https://pith.science/pith/QIZQZXOR42WEVMXIG64KDXVXOR","download_json":"https://pith.science/pith/QIZQZXOR42WEVMXIG64KDXVXOR.json","view_paper":"https://pith.science/paper/QIZQZXOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.09582&json=true","fetch_graph":"https://pith.science/api/pith-number/QIZQZXOR42WEVMXIG64KDXVXOR/graph.json","fetch_events":"https://pith.science/api/pith-number/QIZQZXOR42WEVMXIG64KDXVXOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIZQZXOR42WEVMXIG64KDXVXOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIZQZXOR42WEVMXIG64KDXVXOR/action/storage_attestation","attest_author":"https://pith.science/pith/QIZQZXOR42WEVMXIG64KDXVXOR/action/author_attestation","sign_citation":"https://pith.science/pith/QIZQZXOR42WEVMXIG64KDXVXOR/action/citation_signature","submit_replication":"https://pith.science/pith/QIZQZXOR42WEVMXIG64KDXVXOR/action/replication_record"}},"created_at":"2026-05-18T00:28:35.042301+00:00","updated_at":"2026-05-18T00:28:35.042301+00:00"}