{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SGGKVX5QIXGWA4U6BUKB3FXNN5","short_pith_number":"pith:SGGKVX5Q","schema_version":"1.0","canonical_sha256":"918caadfb045cd60729e0d141d96ed6f70e31e228aa09eac402394117791405f","source":{"kind":"arxiv","id":"1711.08757","version":3},"attestation_state":"computed","paper":{"title":"Deep Expander Networks: Efficient Deep Networks from Graph Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameya Prabhu, Anoop Namboodiri, Girish Varma","submitted_at":"2017-11-23T16:16:04Z","abstract_excerpt":"Efficient CNN designs like ResNets and DenseNet were proposed to improve accuracy vs efficiency trade-offs. They essentially increased the connectivity, allowing efficient information flow across layers. Inspired by these techniques, we propose to model connections between filters of a CNN using graphs which are simultaneously sparse and well connected. Sparsity results in efficiency while well connectedness can preserve the expressive power of the CNNs. We use a well-studied class of graphs from theoretical computer science that satisfies these properties known as Expander graphs. Expander gr"},"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":"1711.08757","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-23T16:16:04Z","cross_cats_sorted":[],"title_canon_sha256":"e76e4a87d76c6de26ac664560ddb4e502422b81004394d409773c8daee1fa943","abstract_canon_sha256":"64b8f174463f79e4fee39e50f380e3bffc06e38ea8474b095c5704a6684c7bdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:47.586382Z","signature_b64":"TDnK/tvsRQuk8rLPraVoFlcaAIlPSrxbNkXibSs0cAgJoLpyx332aeULLmwdeyJ1qf7yuVNFE/BUW3RWxQtBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"918caadfb045cd60729e0d141d96ed6f70e31e228aa09eac402394117791405f","last_reissued_at":"2026-05-18T00:09:47.585771Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:47.585771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Expander Networks: Efficient Deep Networks from Graph Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameya Prabhu, Anoop Namboodiri, Girish Varma","submitted_at":"2017-11-23T16:16:04Z","abstract_excerpt":"Efficient CNN designs like ResNets and DenseNet were proposed to improve accuracy vs efficiency trade-offs. They essentially increased the connectivity, allowing efficient information flow across layers. Inspired by these techniques, we propose to model connections between filters of a CNN using graphs which are simultaneously sparse and well connected. Sparsity results in efficiency while well connectedness can preserve the expressive power of the CNNs. We use a well-studied class of graphs from theoretical computer science that satisfies these properties known as Expander graphs. Expander gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08757","kind":"arxiv","version":3},"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":"1711.08757","created_at":"2026-05-18T00:09:47.585865+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08757v3","created_at":"2026-05-18T00:09:47.585865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08757","created_at":"2026-05-18T00:09:47.585865+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGGKVX5QIXGW","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGGKVX5QIXGWA4U6","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGGKVX5Q","created_at":"2026-05-18T12:31:43.269735+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/SGGKVX5QIXGWA4U6BUKB3FXNN5","json":"https://pith.science/pith/SGGKVX5QIXGWA4U6BUKB3FXNN5.json","graph_json":"https://pith.science/api/pith-number/SGGKVX5QIXGWA4U6BUKB3FXNN5/graph.json","events_json":"https://pith.science/api/pith-number/SGGKVX5QIXGWA4U6BUKB3FXNN5/events.json","paper":"https://pith.science/paper/SGGKVX5Q"},"agent_actions":{"view_html":"https://pith.science/pith/SGGKVX5QIXGWA4U6BUKB3FXNN5","download_json":"https://pith.science/pith/SGGKVX5QIXGWA4U6BUKB3FXNN5.json","view_paper":"https://pith.science/paper/SGGKVX5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08757&json=true","fetch_graph":"https://pith.science/api/pith-number/SGGKVX5QIXGWA4U6BUKB3FXNN5/graph.json","fetch_events":"https://pith.science/api/pith-number/SGGKVX5QIXGWA4U6BUKB3FXNN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGGKVX5QIXGWA4U6BUKB3FXNN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGGKVX5QIXGWA4U6BUKB3FXNN5/action/storage_attestation","attest_author":"https://pith.science/pith/SGGKVX5QIXGWA4U6BUKB3FXNN5/action/author_attestation","sign_citation":"https://pith.science/pith/SGGKVX5QIXGWA4U6BUKB3FXNN5/action/citation_signature","submit_replication":"https://pith.science/pith/SGGKVX5QIXGWA4U6BUKB3FXNN5/action/replication_record"}},"created_at":"2026-05-18T00:09:47.585865+00:00","updated_at":"2026-05-18T00:09:47.585865+00:00"}