{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FFMHMTNIL7Q7QHEWMBAP7H3LFN","short_pith_number":"pith:FFMHMTNI","canonical_record":{"source":{"id":"2408.03728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T12:33:46Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"2157c09ef746d1cc22ad0bf409fd397299e637fada0e3d8c6050427473f29461","abstract_canon_sha256":"32cd4be7155d54ba35658f9b1a2af4439961a413eae9dd3d0305093daf618c58"},"schema_version":"1.0"},"canonical_sha256":"2958764da85fe1f81c966040ff9f6b2b5dd19efb15be6514b53e92cab8f49a20","source":{"kind":"arxiv","id":"2408.03728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03728","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03728v1","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03728","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"FFMHMTNIL7Q7","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"FFMHMTNIL7Q7QHEW","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"FFMHMTNI","created_at":"2026-07-05T08:53:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FFMHMTNIL7Q7QHEWMBAP7H3LFN","target":"record","payload":{"canonical_record":{"source":{"id":"2408.03728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T12:33:46Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"2157c09ef746d1cc22ad0bf409fd397299e637fada0e3d8c6050427473f29461","abstract_canon_sha256":"32cd4be7155d54ba35658f9b1a2af4439961a413eae9dd3d0305093daf618c58"},"schema_version":"1.0"},"canonical_sha256":"2958764da85fe1f81c966040ff9f6b2b5dd19efb15be6514b53e92cab8f49a20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:10.287473Z","signature_b64":"2FQPty30TOJjfvLhskPNzVaEelekHfTjdTlkpRd/9JHT9MGrgITJqwALitk3XXpjqZu+UZDIsR/FW1YqIwz/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2958764da85fe1f81c966040ff9f6b2b5dd19efb15be6514b53e92cab8f49a20","last_reissued_at":"2026-07-05T08:53:10.286865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:10.286865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.03728","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:53:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zpvqqo0XKXJijR3/leuLoxPQ5LK1Yx7ZhG8UxQT5BXM5GjPRG0HggHwCaXLgcxrIIIg3Ic6vBKyZGG3v0yqqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:05:29.422544Z"},"content_sha256":"31a113d93f9cec0f5c19d8f9a788ba788bac7866d07bf9da04f0d5576ebf1d3b","schema_version":"1.0","event_id":"sha256:31a113d93f9cec0f5c19d8f9a788ba788bac7866d07bf9da04f0d5576ebf1d3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FFMHMTNIL7Q7QHEWMBAP7H3LFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Hanyu Hu, Pengxiang Zhao, Ping Li, Xiaoming Yuan, Yi Zheng, Zhefeng Wang","submitted_at":"2024-08-07T12:33:46Z","abstract_excerpt":"Pruning is a critical strategy for compressing trained large language models (LLMs), aiming at substantial memory conservation and computational acceleration without compromising performance. However, existing pruning methods often necessitate inefficient retraining for billion-scale LLMs or rely on heuristic methods such as the optimal brain surgeon framework, which degrade performance. In this paper, we introduce FISTAPruner, the first post-training pruner based on convex optimization models and algorithms. Specifically, we propose a convex optimization model incorporating $\\ell_1$ norm to i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03728","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/2408.03728/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:53:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6Pke5g/2itfXvdWnawIuoM3h3eGDV4eFAQoVzkIEV3HaXgP0HjwNiQEAHs7leLt8KuDlVBEoB7sjWR5AmhtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:05:29.423494Z"},"content_sha256":"db174fa6534415df87da90ee09a715b57f9f258588d7acff506db39e589f1e08","schema_version":"1.0","event_id":"sha256:db174fa6534415df87da90ee09a715b57f9f258588d7acff506db39e589f1e08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FFMHMTNIL7Q7QHEWMBAP7H3LFN/bundle.json","state_url":"https://pith.science/pith/FFMHMTNIL7Q7QHEWMBAP7H3LFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FFMHMTNIL7Q7QHEWMBAP7H3LFN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T01:05:29Z","links":{"resolver":"https://pith.science/pith/FFMHMTNIL7Q7QHEWMBAP7H3LFN","bundle":"https://pith.science/pith/FFMHMTNIL7Q7QHEWMBAP7H3LFN/bundle.json","state":"https://pith.science/pith/FFMHMTNIL7Q7QHEWMBAP7H3LFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FFMHMTNIL7Q7QHEWMBAP7H3LFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FFMHMTNIL7Q7QHEWMBAP7H3LFN","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":"32cd4be7155d54ba35658f9b1a2af4439961a413eae9dd3d0305093daf618c58","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T12:33:46Z","title_canon_sha256":"2157c09ef746d1cc22ad0bf409fd397299e637fada0e3d8c6050427473f29461"},"schema_version":"1.0","source":{"id":"2408.03728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03728","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03728v1","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03728","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"FFMHMTNIL7Q7","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"FFMHMTNIL7Q7QHEW","created_at":"2026-07-05T08:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"FFMHMTNI","created_at":"2026-07-05T08:53:10Z"}],"graph_snapshots":[{"event_id":"sha256:db174fa6534415df87da90ee09a715b57f9f258588d7acff506db39e589f1e08","target":"graph","created_at":"2026-07-05T08:53:10Z","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":[],"endpoint":"/pith/2408.03728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pruning is a critical strategy for compressing trained large language models (LLMs), aiming at substantial memory conservation and computational acceleration without compromising performance. However, existing pruning methods often necessitate inefficient retraining for billion-scale LLMs or rely on heuristic methods such as the optimal brain surgeon framework, which degrade performance. In this paper, we introduce FISTAPruner, the first post-training pruner based on convex optimization models and algorithms. Specifically, we propose a convex optimization model incorporating $\\ell_1$ norm to i","authors_text":"Hanyu Hu, Pengxiang Zhao, Ping Li, Xiaoming Yuan, Yi Zheng, Zhefeng Wang","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T12:33:46Z","title":"A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03728","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":"sha256:31a113d93f9cec0f5c19d8f9a788ba788bac7866d07bf9da04f0d5576ebf1d3b","target":"record","created_at":"2026-07-05T08:53:10Z","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":"32cd4be7155d54ba35658f9b1a2af4439961a413eae9dd3d0305093daf618c58","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T12:33:46Z","title_canon_sha256":"2157c09ef746d1cc22ad0bf409fd397299e637fada0e3d8c6050427473f29461"},"schema_version":"1.0","source":{"id":"2408.03728","kind":"arxiv","version":1}},"canonical_sha256":"2958764da85fe1f81c966040ff9f6b2b5dd19efb15be6514b53e92cab8f49a20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2958764da85fe1f81c966040ff9f6b2b5dd19efb15be6514b53e92cab8f49a20","first_computed_at":"2026-07-05T08:53:10.286865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:10.286865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2FQPty30TOJjfvLhskPNzVaEelekHfTjdTlkpRd/9JHT9MGrgITJqwALitk3XXpjqZu+UZDIsR/FW1YqIwz/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:10.287473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31a113d93f9cec0f5c19d8f9a788ba788bac7866d07bf9da04f0d5576ebf1d3b","sha256:db174fa6534415df87da90ee09a715b57f9f258588d7acff506db39e589f1e08"],"state_sha256":"6dcabee409b4c25b1abcbc1f748c55606f99725e4a45a2323dfca41cfce57808"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5dG9ciF849AVimLEZDo5uMd9YrZOHCVuvr2OJfSDL6ywa5BoL4gRrGROZkBRMOcsx1/g39WIPHUoP1GWkO4dDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:05:29.429230Z","bundle_sha256":"b3ccc716e489ec9f1a336861235bb19c4e5af4e9b4f194b2ec2c8171998ec536"}}