{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MGOPZ3AJS52477YJNHHGFKTU2U","short_pith_number":"pith:MGOPZ3AJ","schema_version":"1.0","canonical_sha256":"619cfcec099775cfff0969ce62aa74d51a6bd6781d7650a7f008d23171c0f297","source":{"kind":"arxiv","id":"2112.10229","version":1},"attestation_state":"computed","paper":{"title":"On Causal Inference for Data-free Structured Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.LG","authors_text":"Anush Sankaran, Ehsan Saboori, Martin Ferianc, Olivier Mastropietro, Quentin Cappart","submitted_at":"2021-12-19T19:01:01Z","abstract_excerpt":"Neural networks (NNs) are making a large impact both on research and industry. Nevertheless, as NNs' accuracy increases, it is followed by an expansion in their size, required number of compute operations and energy consumption. Increase in resource consumption results in NNs' reduced adoption rate and real-world deployment impracticality. Therefore, NNs need to be compressed to make them available to a wider audience and at the same time decrease their runtime costs. In this work, we approach this challenge from a causal inference perspective, and we propose a scoring mechanism to facilitate "},"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":"2112.10229","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-19T19:01:01Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"526abaa119d3b6c23db8b12a0fc5ca27b45870d4c64faf9ff68d7ddfc248d09b","abstract_canon_sha256":"cbde2d5295c8c9bab7fa50ec57e560dd862ecaf4e16b3a69cd134c4cabec1e84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:12.645767Z","signature_b64":"Mh4sdDWig8Uth+4yRuINMkoJPX27P/Hw3I5qucK7dh1kU6Cg7aiWLL3NS7pSSJizGxpciHxGGMb3E6yOF65UAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"619cfcec099775cfff0969ce62aa74d51a6bd6781d7650a7f008d23171c0f297","last_reissued_at":"2026-07-05T03:42:12.645389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:12.645389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Causal Inference for Data-free Structured Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.LG","authors_text":"Anush Sankaran, Ehsan Saboori, Martin Ferianc, Olivier Mastropietro, Quentin Cappart","submitted_at":"2021-12-19T19:01:01Z","abstract_excerpt":"Neural networks (NNs) are making a large impact both on research and industry. Nevertheless, as NNs' accuracy increases, it is followed by an expansion in their size, required number of compute operations and energy consumption. Increase in resource consumption results in NNs' reduced adoption rate and real-world deployment impracticality. Therefore, NNs need to be compressed to make them available to a wider audience and at the same time decrease their runtime costs. In this work, we approach this challenge from a causal inference perspective, and we propose a scoring mechanism to facilitate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10229","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.10229/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2112.10229","created_at":"2026-07-05T03:42:12.645451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10229v1","created_at":"2026-07-05T03:42:12.645451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10229","created_at":"2026-07-05T03:42:12.645451+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGOPZ3AJS524","created_at":"2026-07-05T03:42:12.645451+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGOPZ3AJS52477YJ","created_at":"2026-07-05T03:42:12.645451+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGOPZ3AJ","created_at":"2026-07-05T03:42:12.645451+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/MGOPZ3AJS52477YJNHHGFKTU2U","json":"https://pith.science/pith/MGOPZ3AJS52477YJNHHGFKTU2U.json","graph_json":"https://pith.science/api/pith-number/MGOPZ3AJS52477YJNHHGFKTU2U/graph.json","events_json":"https://pith.science/api/pith-number/MGOPZ3AJS52477YJNHHGFKTU2U/events.json","paper":"https://pith.science/paper/MGOPZ3AJ"},"agent_actions":{"view_html":"https://pith.science/pith/MGOPZ3AJS52477YJNHHGFKTU2U","download_json":"https://pith.science/pith/MGOPZ3AJS52477YJNHHGFKTU2U.json","view_paper":"https://pith.science/paper/MGOPZ3AJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10229&json=true","fetch_graph":"https://pith.science/api/pith-number/MGOPZ3AJS52477YJNHHGFKTU2U/graph.json","fetch_events":"https://pith.science/api/pith-number/MGOPZ3AJS52477YJNHHGFKTU2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGOPZ3AJS52477YJNHHGFKTU2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGOPZ3AJS52477YJNHHGFKTU2U/action/storage_attestation","attest_author":"https://pith.science/pith/MGOPZ3AJS52477YJNHHGFKTU2U/action/author_attestation","sign_citation":"https://pith.science/pith/MGOPZ3AJS52477YJNHHGFKTU2U/action/citation_signature","submit_replication":"https://pith.science/pith/MGOPZ3AJS52477YJNHHGFKTU2U/action/replication_record"}},"created_at":"2026-07-05T03:42:12.645451+00:00","updated_at":"2026-07-05T03:42:12.645451+00:00"}