{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UEU2SAIPUPMKJQIIZEAC7CPXNC","short_pith_number":"pith:UEU2SAIP","schema_version":"1.0","canonical_sha256":"a129a9010fa3d8a4c108c9002f89f768b6b3fd805e91648cf05a2aceaedfbd9e","source":{"kind":"arxiv","id":"2402.07839","version":2},"attestation_state":"computed","paper":{"title":"Towards Meta-Pruning via Optimal Transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Theus, Friedrich Wicke, Olin Geimer, Sidak Pal Singh, Sotiris Anagnostidis, Thomas Hofmann","submitted_at":"2024-02-12T17:50:56Z","abstract_excerpt":"Structural pruning of neural networks conventionally relies on identifying and discarding less important neurons, a practice often resulting in significant accuracy loss that necessitates subsequent fine-tuning efforts. This paper introduces a novel approach named Intra-Fusion, challenging this prevailing pruning paradigm. Unlike existing methods that focus on designing meaningful neuron importance metrics, Intra-Fusion redefines the overlying pruning procedure. Through utilizing the concepts of model fusion and Optimal Transport, we leverage an agnostically given importance metric to arrive a"},"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":"2402.07839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-12T17:50:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"95d49d382273408dc68f92852bfc0cef18a4b19b3379ec0914e705aa3bef03bf","abstract_canon_sha256":"9fb9e0516e8ac36ce2a2ff0a13913b1dabde984c7b4fc94e58ea59471424287b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:23.809140Z","signature_b64":"dZKtqQTEowH8gjdV0JDwZ3un+nEmI4uwpnA4X4aYDZV40TdtTVgmtu+gOknVjxnPLaq7IsheEdBzYf6fpvObAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a129a9010fa3d8a4c108c9002f89f768b6b3fd805e91648cf05a2aceaedfbd9e","last_reissued_at":"2026-07-05T07:44:23.808759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:23.808759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Meta-Pruning via Optimal Transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Theus, Friedrich Wicke, Olin Geimer, Sidak Pal Singh, Sotiris Anagnostidis, Thomas Hofmann","submitted_at":"2024-02-12T17:50:56Z","abstract_excerpt":"Structural pruning of neural networks conventionally relies on identifying and discarding less important neurons, a practice often resulting in significant accuracy loss that necessitates subsequent fine-tuning efforts. This paper introduces a novel approach named Intra-Fusion, challenging this prevailing pruning paradigm. Unlike existing methods that focus on designing meaningful neuron importance metrics, Intra-Fusion redefines the overlying pruning procedure. Through utilizing the concepts of model fusion and Optimal Transport, we leverage an agnostically given importance metric to arrive a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07839","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.07839/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":"2402.07839","created_at":"2026-07-05T07:44:23.808814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07839v2","created_at":"2026-07-05T07:44:23.808814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07839","created_at":"2026-07-05T07:44:23.808814+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEU2SAIPUPMK","created_at":"2026-07-05T07:44:23.808814+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEU2SAIPUPMKJQII","created_at":"2026-07-05T07:44:23.808814+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEU2SAIP","created_at":"2026-07-05T07:44:23.808814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10216","citing_title":"Forget the Data and Fine-Tuning! Just Fold the Network to Compress","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC","json":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC.json","graph_json":"https://pith.science/api/pith-number/UEU2SAIPUPMKJQIIZEAC7CPXNC/graph.json","events_json":"https://pith.science/api/pith-number/UEU2SAIPUPMKJQIIZEAC7CPXNC/events.json","paper":"https://pith.science/paper/UEU2SAIP"},"agent_actions":{"view_html":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC","download_json":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC.json","view_paper":"https://pith.science/paper/UEU2SAIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07839&json=true","fetch_graph":"https://pith.science/api/pith-number/UEU2SAIPUPMKJQIIZEAC7CPXNC/graph.json","fetch_events":"https://pith.science/api/pith-number/UEU2SAIPUPMKJQIIZEAC7CPXNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC/action/storage_attestation","attest_author":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC/action/author_attestation","sign_citation":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC/action/citation_signature","submit_replication":"https://pith.science/pith/UEU2SAIPUPMKJQIIZEAC7CPXNC/action/replication_record"}},"created_at":"2026-07-05T07:44:23.808814+00:00","updated_at":"2026-07-05T07:44:23.808814+00:00"}