{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OXAK6PTBFWMWUB7Y3W7U4F66NA","short_pith_number":"pith:OXAK6PTB","schema_version":"1.0","canonical_sha256":"75c0af3e612d996a07f8ddbf4e17de682b53a8d7a6d2f4a722eafff1f83ee1f8","source":{"kind":"arxiv","id":"2605.17289","version":1},"attestation_state":"computed","paper":{"title":"LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mahyar Najibi, Mohammad Mozaffari, Mohammad Rastegari, Younes Hourri","submitted_at":"2026-05-17T07:01:13Z","abstract_excerpt":"Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm. State-of-the-art methods for unstructured LLM pruning are layer-wise surrogates derived from the Optimal Brain Surgeon principle, and they sacrifice end-to-end accuracy, especially under aggressive sparsity. End-to-end alternatives such as MaskLLM and PATCH show that learnable masks can close this gap, but their categorical-over-patterns parameterization scales with the number of valid masks per row and does not port to the un"},"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":"2605.17289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T07:01:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5b6e4109d172d66eb1ef7ae68a6f537211ad8806eafbd743e4204362b7c7b133","abstract_canon_sha256":"1bbf71a945e9d766ae093aa63c5350f40d3fc3dd416530e97b963ec3ef28808e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:50.127594Z","signature_b64":"Hokk9Z64uE4sVmmMRV6PF8DZOyei0yZhcrrBOLsWuQJUgvd3Y1XhR7EtONRKQ8Zt9rZbkzdu31OlokMo8mN3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75c0af3e612d996a07f8ddbf4e17de682b53a8d7a6d2f4a722eafff1f83ee1f8","last_reissued_at":"2026-05-20T00:03:50.126688Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:50.126688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mahyar Najibi, Mohammad Mozaffari, Mohammad Rastegari, Younes Hourri","submitted_at":"2026-05-17T07:01:13Z","abstract_excerpt":"Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm. State-of-the-art methods for unstructured LLM pruning are layer-wise surrogates derived from the Optimal Brain Surgeon principle, and they sacrifice end-to-end accuracy, especially under aggressive sparsity. End-to-end alternatives such as MaskLLM and PATCH show that learnable masks can close this gap, but their categorical-over-patterns parameterization scales with the number of valid masks per row and does not port to the un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17289","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/2605.17289/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.817323Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.767509Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8989bac6b21d2406562e654ff15103c18260702d026264ae485e9c1723a332f3"},"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":"2605.17289","created_at":"2026-05-20T00:03:50.126817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17289v1","created_at":"2026-05-20T00:03:50.126817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17289","created_at":"2026-05-20T00:03:50.126817+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXAK6PTBFWMW","created_at":"2026-05-20T00:03:50.126817+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXAK6PTBFWMWUB7Y","created_at":"2026-05-20T00:03:50.126817+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXAK6PTB","created_at":"2026-05-20T00:03:50.126817+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/OXAK6PTBFWMWUB7Y3W7U4F66NA","json":"https://pith.science/pith/OXAK6PTBFWMWUB7Y3W7U4F66NA.json","graph_json":"https://pith.science/api/pith-number/OXAK6PTBFWMWUB7Y3W7U4F66NA/graph.json","events_json":"https://pith.science/api/pith-number/OXAK6PTBFWMWUB7Y3W7U4F66NA/events.json","paper":"https://pith.science/paper/OXAK6PTB"},"agent_actions":{"view_html":"https://pith.science/pith/OXAK6PTBFWMWUB7Y3W7U4F66NA","download_json":"https://pith.science/pith/OXAK6PTBFWMWUB7Y3W7U4F66NA.json","view_paper":"https://pith.science/paper/OXAK6PTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17289&json=true","fetch_graph":"https://pith.science/api/pith-number/OXAK6PTBFWMWUB7Y3W7U4F66NA/graph.json","fetch_events":"https://pith.science/api/pith-number/OXAK6PTBFWMWUB7Y3W7U4F66NA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXAK6PTBFWMWUB7Y3W7U4F66NA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXAK6PTBFWMWUB7Y3W7U4F66NA/action/storage_attestation","attest_author":"https://pith.science/pith/OXAK6PTBFWMWUB7Y3W7U4F66NA/action/author_attestation","sign_citation":"https://pith.science/pith/OXAK6PTBFWMWUB7Y3W7U4F66NA/action/citation_signature","submit_replication":"https://pith.science/pith/OXAK6PTBFWMWUB7Y3W7U4F66NA/action/replication_record"}},"created_at":"2026-05-20T00:03:50.126817+00:00","updated_at":"2026-05-20T00:03:50.126817+00:00"}