{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PSVOLLNAHZYCK4FPZSCYWJIXVS","short_pith_number":"pith:PSVOLLNA","schema_version":"1.0","canonical_sha256":"7caae5ada03e702570afcc858b2517aca12d3185ec3c653bc79323433837da1e","source":{"kind":"arxiv","id":"1905.11428","version":1},"attestation_state":"computed","paper":{"title":"Equivalent and Approximate Transformations of Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Kumar, Srikumar Ramalingam, Thiago Serra","submitted_at":"2019-05-27T18:05:28Z","abstract_excerpt":"Two networks are equivalent if they produce the same output for any given input. In this paper, we study the possibility of transforming a deep neural network to another network with a different number of units or layers, which can be either equivalent, a local exact approximation, or a global linear approximation of the original network. On the practical side, we show that certain rectified linear units (ReLUs) can be safely removed from a network if they are always active or inactive for any valid input. If we only need an equivalent network for a smaller domain, then more units can be remov"},"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":"1905.11428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T18:05:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"847518bac6c91cb7ee2ae170aa9b02fdf04e74b0097b97fb12419a946a8a53a6","abstract_canon_sha256":"c6c49bd7d9f49a1d330845bbaeebf9a062ccedb72ab5286b4fc23ad29aec572a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:53.443065Z","signature_b64":"ShZegQVN7qcoLNj8UmcsF9yb7LqVgsSD95sdD7d1O6sr94aZ2Sz3e4hqVYgj64Vra7Z1JFSjf1RzWW/LYNgABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7caae5ada03e702570afcc858b2517aca12d3185ec3c653bc79323433837da1e","last_reissued_at":"2026-05-17T23:44:53.442444Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:53.442444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivalent and Approximate Transformations of Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Kumar, Srikumar Ramalingam, Thiago Serra","submitted_at":"2019-05-27T18:05:28Z","abstract_excerpt":"Two networks are equivalent if they produce the same output for any given input. In this paper, we study the possibility of transforming a deep neural network to another network with a different number of units or layers, which can be either equivalent, a local exact approximation, or a global linear approximation of the original network. On the practical side, we show that certain rectified linear units (ReLUs) can be safely removed from a network if they are always active or inactive for any valid input. If we only need an equivalent network for a smaller domain, then more units can be remov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11428","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":""},"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":"1905.11428","created_at":"2026-05-17T23:44:53.442541+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11428v1","created_at":"2026-05-17T23:44:53.442541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11428","created_at":"2026-05-17T23:44:53.442541+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSVOLLNAHZYC","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSVOLLNAHZYCK4FP","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSVOLLNA","created_at":"2026-05-18T12:33:24.271573+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/PSVOLLNAHZYCK4FPZSCYWJIXVS","json":"https://pith.science/pith/PSVOLLNAHZYCK4FPZSCYWJIXVS.json","graph_json":"https://pith.science/api/pith-number/PSVOLLNAHZYCK4FPZSCYWJIXVS/graph.json","events_json":"https://pith.science/api/pith-number/PSVOLLNAHZYCK4FPZSCYWJIXVS/events.json","paper":"https://pith.science/paper/PSVOLLNA"},"agent_actions":{"view_html":"https://pith.science/pith/PSVOLLNAHZYCK4FPZSCYWJIXVS","download_json":"https://pith.science/pith/PSVOLLNAHZYCK4FPZSCYWJIXVS.json","view_paper":"https://pith.science/paper/PSVOLLNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11428&json=true","fetch_graph":"https://pith.science/api/pith-number/PSVOLLNAHZYCK4FPZSCYWJIXVS/graph.json","fetch_events":"https://pith.science/api/pith-number/PSVOLLNAHZYCK4FPZSCYWJIXVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSVOLLNAHZYCK4FPZSCYWJIXVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSVOLLNAHZYCK4FPZSCYWJIXVS/action/storage_attestation","attest_author":"https://pith.science/pith/PSVOLLNAHZYCK4FPZSCYWJIXVS/action/author_attestation","sign_citation":"https://pith.science/pith/PSVOLLNAHZYCK4FPZSCYWJIXVS/action/citation_signature","submit_replication":"https://pith.science/pith/PSVOLLNAHZYCK4FPZSCYWJIXVS/action/replication_record"}},"created_at":"2026-05-17T23:44:53.442541+00:00","updated_at":"2026-05-17T23:44:53.442541+00:00"}