{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GBKQKYKMQYFDDTHOLLAJ6KCEBC","short_pith_number":"pith:GBKQKYKM","schema_version":"1.0","canonical_sha256":"305505614c860a31ccee5ac09f284408acd11bef3d3ca260ea3cc7dd8b9c458b","source":{"kind":"arxiv","id":"2501.18980","version":1},"attestation_state":"computed","paper":{"title":"Symmetric Pruning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kai Yi, Peter Richt\\'arik","submitted_at":"2025-01-31T09:23:06Z","abstract_excerpt":"Popular post-training pruning methods such as Wanda and RIA are known for their simple, yet effective, designs that have shown exceptional empirical performance. Wanda optimizes performance through calibrated activations during pruning, while RIA emphasizes the relative, rather than absolute, importance of weight elements. Despite their practical success, a thorough theoretical foundation explaining these outcomes has been lacking. This paper introduces new theoretical insights that redefine the standard minimization objective for pruning, offering a deeper understanding of the factors contrib"},"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":"2501.18980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T09:23:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0da7c4e155c032c10ad2f3fff5a20925828e654568520e458a84e1ca4864ae96","abstract_canon_sha256":"7e494185f5bfbbdc59d77b30ed726968a046931fb9900051ad332462b535afc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:54.281754Z","signature_b64":"TNBcg9nuSpCgiZrZFIrer8zLjooPQqXs4wUJoPfk4cEt+TSahHZViMQNabY1xrJ60vHeyEokYNP2+XDwLNgHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"305505614c860a31ccee5ac09f284408acd11bef3d3ca260ea3cc7dd8b9c458b","last_reissued_at":"2026-07-05T10:07:54.281276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:54.281276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symmetric Pruning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kai Yi, Peter Richt\\'arik","submitted_at":"2025-01-31T09:23:06Z","abstract_excerpt":"Popular post-training pruning methods such as Wanda and RIA are known for their simple, yet effective, designs that have shown exceptional empirical performance. Wanda optimizes performance through calibrated activations during pruning, while RIA emphasizes the relative, rather than absolute, importance of weight elements. Despite their practical success, a thorough theoretical foundation explaining these outcomes has been lacking. This paper introduces new theoretical insights that redefine the standard minimization objective for pruning, offering a deeper understanding of the factors contrib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18980","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/2501.18980/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":"2501.18980","created_at":"2026-07-05T10:07:54.281345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18980v1","created_at":"2026-07-05T10:07:54.281345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18980","created_at":"2026-07-05T10:07:54.281345+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBKQKYKMQYFD","created_at":"2026-07-05T10:07:54.281345+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBKQKYKMQYFDDTHO","created_at":"2026-07-05T10:07:54.281345+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBKQKYKM","created_at":"2026-07-05T10:07:54.281345+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/GBKQKYKMQYFDDTHOLLAJ6KCEBC","json":"https://pith.science/pith/GBKQKYKMQYFDDTHOLLAJ6KCEBC.json","graph_json":"https://pith.science/api/pith-number/GBKQKYKMQYFDDTHOLLAJ6KCEBC/graph.json","events_json":"https://pith.science/api/pith-number/GBKQKYKMQYFDDTHOLLAJ6KCEBC/events.json","paper":"https://pith.science/paper/GBKQKYKM"},"agent_actions":{"view_html":"https://pith.science/pith/GBKQKYKMQYFDDTHOLLAJ6KCEBC","download_json":"https://pith.science/pith/GBKQKYKMQYFDDTHOLLAJ6KCEBC.json","view_paper":"https://pith.science/paper/GBKQKYKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18980&json=true","fetch_graph":"https://pith.science/api/pith-number/GBKQKYKMQYFDDTHOLLAJ6KCEBC/graph.json","fetch_events":"https://pith.science/api/pith-number/GBKQKYKMQYFDDTHOLLAJ6KCEBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBKQKYKMQYFDDTHOLLAJ6KCEBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBKQKYKMQYFDDTHOLLAJ6KCEBC/action/storage_attestation","attest_author":"https://pith.science/pith/GBKQKYKMQYFDDTHOLLAJ6KCEBC/action/author_attestation","sign_citation":"https://pith.science/pith/GBKQKYKMQYFDDTHOLLAJ6KCEBC/action/citation_signature","submit_replication":"https://pith.science/pith/GBKQKYKMQYFDDTHOLLAJ6KCEBC/action/replication_record"}},"created_at":"2026-07-05T10:07:54.281345+00:00","updated_at":"2026-07-05T10:07:54.281345+00:00"}