{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3OUCYKSDLCAL37WNUHQTSXMV4B","short_pith_number":"pith:3OUCYKSD","schema_version":"1.0","canonical_sha256":"dba82c2a435880bdfecda1e1395d95e0435e33e2d7b01f2f07eb2ae9ab5f86b8","source":{"kind":"arxiv","id":"2311.10468","version":1},"attestation_state":"computed","paper":{"title":"Using Cooperative Game Theory to Prune Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Benjamin Kempinski, Daphne Cornelisse, Mauricio Diaz-Ortiz Jr, Tal Kachman, Yoram Bachrach","submitted_at":"2023-11-17T11:48:10Z","abstract_excerpt":"We show how solution concepts from cooperative game theory can be used to tackle the problem of pruning neural networks.\n  The ever-growing size of deep neural networks (DNNs) increases their performance, but also their computational requirements. We introduce a method called Game Theory Assisted Pruning (GTAP), which reduces the neural network's size while preserving its predictive accuracy. GTAP is based on eliminating neurons in the network based on an estimation of their joint impact on the prediction quality through game theoretic solutions. Specifically, we use a power index akin to the "},"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":"2311.10468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-17T11:48:10Z","cross_cats_sorted":["cs.AI","cs.CE","cs.GT","cs.MA"],"title_canon_sha256":"ce5f237a84199ec1f4e2b52c46ff50cd30d97c93f23439afd3cf91936bb08cc9","abstract_canon_sha256":"67a76fa4174c5207a2af538afc7cabfd78b3d445ade5bb97674545a447b64f7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:52.710182Z","signature_b64":"Ao5aX3m3zZRArLRj2tkDpZ9mxUhSz/ugq7gj/BuyvgjTWVppByouDVTdlsJWLeCJ7G3gCyeLC6X7c2LYKSxbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dba82c2a435880bdfecda1e1395d95e0435e33e2d7b01f2f07eb2ae9ab5f86b8","last_reissued_at":"2026-07-05T07:13:52.709769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:52.709769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Cooperative Game Theory to Prune Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Benjamin Kempinski, Daphne Cornelisse, Mauricio Diaz-Ortiz Jr, Tal Kachman, Yoram Bachrach","submitted_at":"2023-11-17T11:48:10Z","abstract_excerpt":"We show how solution concepts from cooperative game theory can be used to tackle the problem of pruning neural networks.\n  The ever-growing size of deep neural networks (DNNs) increases their performance, but also their computational requirements. We introduce a method called Game Theory Assisted Pruning (GTAP), which reduces the neural network's size while preserving its predictive accuracy. GTAP is based on eliminating neurons in the network based on an estimation of their joint impact on the prediction quality through game theoretic solutions. Specifically, we use a power index akin to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10468","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/2311.10468/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":"2311.10468","created_at":"2026-07-05T07:13:52.709823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10468v1","created_at":"2026-07-05T07:13:52.709823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10468","created_at":"2026-07-05T07:13:52.709823+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OUCYKSDLCAL","created_at":"2026-07-05T07:13:52.709823+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OUCYKSDLCAL37WN","created_at":"2026-07-05T07:13:52.709823+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OUCYKSD","created_at":"2026-07-05T07:13:52.709823+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/3OUCYKSDLCAL37WNUHQTSXMV4B","json":"https://pith.science/pith/3OUCYKSDLCAL37WNUHQTSXMV4B.json","graph_json":"https://pith.science/api/pith-number/3OUCYKSDLCAL37WNUHQTSXMV4B/graph.json","events_json":"https://pith.science/api/pith-number/3OUCYKSDLCAL37WNUHQTSXMV4B/events.json","paper":"https://pith.science/paper/3OUCYKSD"},"agent_actions":{"view_html":"https://pith.science/pith/3OUCYKSDLCAL37WNUHQTSXMV4B","download_json":"https://pith.science/pith/3OUCYKSDLCAL37WNUHQTSXMV4B.json","view_paper":"https://pith.science/paper/3OUCYKSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10468&json=true","fetch_graph":"https://pith.science/api/pith-number/3OUCYKSDLCAL37WNUHQTSXMV4B/graph.json","fetch_events":"https://pith.science/api/pith-number/3OUCYKSDLCAL37WNUHQTSXMV4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OUCYKSDLCAL37WNUHQTSXMV4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OUCYKSDLCAL37WNUHQTSXMV4B/action/storage_attestation","attest_author":"https://pith.science/pith/3OUCYKSDLCAL37WNUHQTSXMV4B/action/author_attestation","sign_citation":"https://pith.science/pith/3OUCYKSDLCAL37WNUHQTSXMV4B/action/citation_signature","submit_replication":"https://pith.science/pith/3OUCYKSDLCAL37WNUHQTSXMV4B/action/replication_record"}},"created_at":"2026-07-05T07:13:52.709823+00:00","updated_at":"2026-07-05T07:13:52.709823+00:00"}