{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QL5O2VHNYYQDEYG6MBCXN6EYYY","short_pith_number":"pith:QL5O2VHN","schema_version":"1.0","canonical_sha256":"82faed54edc6203260de604576f898c61cda402aa478ca47731d54282fd6d1e2","source":{"kind":"arxiv","id":"1811.03060","version":2},"attestation_state":"computed","paper":{"title":"FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashutosh Adhikari, Jimmy Lin, Raphael Tang","submitted_at":"2018-11-07T18:21:25Z","abstract_excerpt":"There exists a plethora of techniques for inducing structured sparsity in parametric models during the optimization process, with the final goal of resource-efficient inference. However, few methods target a specific number of floating-point operations (FLOPs) as part of the optimization objective, despite many reporting FLOPs as part of the results. Furthermore, a one-size-fits-all approach ignores realistic system constraints, which differ significantly between, say, a GPU and a mobile phone -- FLOPs on the former incur less latency than on the latter; thus, it is important for practitioners"},"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":"1811.03060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-07T18:21:25Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2a2d0509307d26e9b268ab6f5c830fcffc10089165421a43bdbf61572c808626","abstract_canon_sha256":"e0f5135f2eb83abfd2f62f46a1d6c7589990b304792a36e2261b7244b363cabb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:07.858865Z","signature_b64":"n+WuvtDh6au91pRsnKkab8yiVeK10nDzIdYpxVQtPK0OuoBQw+oZQr3rnszNaMrb1oZ6VQD+rOFISu7hrqI6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82faed54edc6203260de604576f898c61cda402aa478ca47731d54282fd6d1e2","last_reissued_at":"2026-05-18T00:00:07.858331Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:07.858331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashutosh Adhikari, Jimmy Lin, Raphael Tang","submitted_at":"2018-11-07T18:21:25Z","abstract_excerpt":"There exists a plethora of techniques for inducing structured sparsity in parametric models during the optimization process, with the final goal of resource-efficient inference. However, few methods target a specific number of floating-point operations (FLOPs) as part of the optimization objective, despite many reporting FLOPs as part of the results. Furthermore, a one-size-fits-all approach ignores realistic system constraints, which differ significantly between, say, a GPU and a mobile phone -- FLOPs on the former incur less latency than on the latter; thus, it is important for practitioners"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03060","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":"1811.03060","created_at":"2026-05-18T00:00:07.858426+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.03060v2","created_at":"2026-05-18T00:00:07.858426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03060","created_at":"2026-05-18T00:00:07.858426+00:00"},{"alias_kind":"pith_short_12","alias_value":"QL5O2VHNYYQD","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QL5O2VHNYYQDEYG6","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QL5O2VHN","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02519","citing_title":"Neuron ranking -- an informed way to condense convolutional neural networks architecture","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY","json":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY.json","graph_json":"https://pith.science/api/pith-number/QL5O2VHNYYQDEYG6MBCXN6EYYY/graph.json","events_json":"https://pith.science/api/pith-number/QL5O2VHNYYQDEYG6MBCXN6EYYY/events.json","paper":"https://pith.science/paper/QL5O2VHN"},"agent_actions":{"view_html":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY","download_json":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY.json","view_paper":"https://pith.science/paper/QL5O2VHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.03060&json=true","fetch_graph":"https://pith.science/api/pith-number/QL5O2VHNYYQDEYG6MBCXN6EYYY/graph.json","fetch_events":"https://pith.science/api/pith-number/QL5O2VHNYYQDEYG6MBCXN6EYYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY/action/storage_attestation","attest_author":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY/action/author_attestation","sign_citation":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY/action/citation_signature","submit_replication":"https://pith.science/pith/QL5O2VHNYYQDEYG6MBCXN6EYYY/action/replication_record"}},"created_at":"2026-05-18T00:00:07.858426+00:00","updated_at":"2026-05-18T00:00:07.858426+00:00"}