{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OXAK6PTBFWMWUB7Y3W7U4F66NA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1bbf71a945e9d766ae093aa63c5350f40d3fc3dd416530e97b963ec3ef28808e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T07:01:13Z","title_canon_sha256":"5b6e4109d172d66eb1ef7ae68a6f537211ad8806eafbd743e4204362b7c7b133"},"schema_version":"1.0","source":{"id":"2605.17289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17289","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17289v1","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17289","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"OXAK6PTBFWMW","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"OXAK6PTBFWMWUB7Y","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"OXAK6PTB","created_at":"2026-05-20T00:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:dcc37c40b2a9897c3f2094ad0f6a5df5ba8f5e6bdd8b913b089415098e581ea8","target":"graph","created_at":"2026-05-20T00:03:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.17289/integrity.json","findings":[],"snapshot_sha256":"8989bac6b21d2406562e654ff15103c18260702d026264ae485e9c1723a332f3","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mahyar Najibi, Mohammad Mozaffari, Mohammad Rastegari, Younes Hourri","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T07:01:13Z","title":"LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17289","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:122bcd1f50b8cfe35ff5ae91b7cb1ca25c9a06d2a25bc5942348ce1ff5059738","target":"record","created_at":"2026-05-20T00:03:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1bbf71a945e9d766ae093aa63c5350f40d3fc3dd416530e97b963ec3ef28808e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T07:01:13Z","title_canon_sha256":"5b6e4109d172d66eb1ef7ae68a6f537211ad8806eafbd743e4204362b7c7b133"},"schema_version":"1.0","source":{"id":"2605.17289","kind":"arxiv","version":1}},"canonical_sha256":"75c0af3e612d996a07f8ddbf4e17de682b53a8d7a6d2f4a722eafff1f83ee1f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75c0af3e612d996a07f8ddbf4e17de682b53a8d7a6d2f4a722eafff1f83ee1f8","first_computed_at":"2026-05-20T00:03:50.126688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:50.126688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hokk9Z64uE4sVmmMRV6PF8DZOyei0yZhcrrBOLsWuQJUgvd3Y1XhR7EtONRKQ8Zt9rZbkzdu31OlokMo8mN3CA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:50.127594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:122bcd1f50b8cfe35ff5ae91b7cb1ca25c9a06d2a25bc5942348ce1ff5059738","sha256:dcc37c40b2a9897c3f2094ad0f6a5df5ba8f5e6bdd8b913b089415098e581ea8"],"state_sha256":"a22af3db2e8a6d93b9e6306716bb5446edda135e1263f361f2c58f2f6ad35b79"}