{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UELN7ES53V5J7SKUHW343WJZGK","short_pith_number":"pith:UELN7ES5","canonical_record":{"source":{"id":"2502.10735","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T09:17:38Z","cross_cats_sorted":[],"title_canon_sha256":"e00792f31129d3eaf88791cff971f19d77529849f494355ac882984f79ffec0d","abstract_canon_sha256":"3b72522fc4d134173b56b5483cb1c4fff74157efe2459f8746c1bdd72c6b808b"},"schema_version":"1.0"},"canonical_sha256":"a116df925ddd7a9fc9543db7cdd9393286b140e39165396ccaa487733e9f91a5","source":{"kind":"arxiv","id":"2502.10735","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10735","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10735v2","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10735","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"UELN7ES53V5J","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"UELN7ES53V5J7SKU","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"UELN7ES5","created_at":"2026-07-05T11:08:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UELN7ES53V5J7SKUHW343WJZGK","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10735","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T09:17:38Z","cross_cats_sorted":[],"title_canon_sha256":"e00792f31129d3eaf88791cff971f19d77529849f494355ac882984f79ffec0d","abstract_canon_sha256":"3b72522fc4d134173b56b5483cb1c4fff74157efe2459f8746c1bdd72c6b808b"},"schema_version":"1.0"},"canonical_sha256":"a116df925ddd7a9fc9543db7cdd9393286b140e39165396ccaa487733e9f91a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:16.421428Z","signature_b64":"rdeCZvHMmw7cZtWFhr02+o7iOadqRVIwc89apgcLI0aMCoNCuIn+CVK2d5rQMQrs0GcTl2pur+9kx36xGq2ACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a116df925ddd7a9fc9543db7cdd9393286b140e39165396ccaa487733e9f91a5","last_reissued_at":"2026-07-05T11:08:16.420897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:16.420897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10735","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YKcEDeKTigSm7RXK+MFlJyVYSLS26awRh7vyj+YDUbEdpO94mFuq+nCDbXr+crEJXqopGDqaIWcopjnOqSfaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:16:49.317067Z"},"content_sha256":"407e952d3d26443c600c46986544ca743366a5818699b9df8d4b2fa579d9284d","schema_version":"1.0","event_id":"sha256:407e952d3d26443c600c46986544ca743366a5818699b9df8d4b2fa579d9284d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UELN7ES53V5J7SKUHW343WJZGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowei He, Han Wu, Linqi Song, Shuqi Liu","submitted_at":"2025-02-15T09:17:38Z","abstract_excerpt":"Post-training pruning has emerged as a crucial optimization technique as large language models (LLMs) continue to grow rapidly. However, the significant variations in weight distributions across different LLMs make fixed pruning strategies inadequate for multiple models. In this paper, we introduce \\textbf{\\textsc{OptiShear}}, an efficient evolutionary optimization framework for adaptive LLM pruning. Our framework features two key innovations: an effective search space built on our Meta pruning metric to handle diverse weight distributions, and a model-wise reconstruction error for rapid evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10735","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/2502.10735/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":"2026-07-05T11:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"682Bn0UQY5U5ZYHDdw8jtZbCwje30poJ1iMXXXA3CeF47BukYoBjqNux+a+wdeGuGdkgt5oC+vl5d13fNOm1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:16:49.318491Z"},"content_sha256":"1c991065f615c233e4e33b71933354f947f586a73b987699d37f23791a5802ec","schema_version":"1.0","event_id":"sha256:1c991065f615c233e4e33b71933354f947f586a73b987699d37f23791a5802ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UELN7ES53V5J7SKUHW343WJZGK/bundle.json","state_url":"https://pith.science/pith/UELN7ES53V5J7SKUHW343WJZGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UELN7ES53V5J7SKUHW343WJZGK/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":"2026-08-17T19:16:49Z","links":{"resolver":"https://pith.science/pith/UELN7ES53V5J7SKUHW343WJZGK","bundle":"https://pith.science/pith/UELN7ES53V5J7SKUHW343WJZGK/bundle.json","state":"https://pith.science/pith/UELN7ES53V5J7SKUHW343WJZGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UELN7ES53V5J7SKUHW343WJZGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UELN7ES53V5J7SKUHW343WJZGK","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":"3b72522fc4d134173b56b5483cb1c4fff74157efe2459f8746c1bdd72c6b808b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T09:17:38Z","title_canon_sha256":"e00792f31129d3eaf88791cff971f19d77529849f494355ac882984f79ffec0d"},"schema_version":"1.0","source":{"id":"2502.10735","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10735","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10735v2","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10735","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"UELN7ES53V5J","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"UELN7ES53V5J7SKU","created_at":"2026-07-05T11:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"UELN7ES5","created_at":"2026-07-05T11:08:16Z"}],"graph_snapshots":[{"event_id":"sha256:1c991065f615c233e4e33b71933354f947f586a73b987699d37f23791a5802ec","target":"graph","created_at":"2026-07-05T11:08:16Z","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/2502.10735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training pruning has emerged as a crucial optimization technique as large language models (LLMs) continue to grow rapidly. However, the significant variations in weight distributions across different LLMs make fixed pruning strategies inadequate for multiple models. In this paper, we introduce \\textbf{\\textsc{OptiShear}}, an efficient evolutionary optimization framework for adaptive LLM pruning. Our framework features two key innovations: an effective search space built on our Meta pruning metric to handle diverse weight distributions, and a model-wise reconstruction error for rapid evalu","authors_text":"Bowei He, Han Wu, Linqi Song, Shuqi Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T09:17:38Z","title":"Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10735","kind":"arxiv","version":2},"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":"sha256:407e952d3d26443c600c46986544ca743366a5818699b9df8d4b2fa579d9284d","target":"record","created_at":"2026-07-05T11:08:16Z","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":"3b72522fc4d134173b56b5483cb1c4fff74157efe2459f8746c1bdd72c6b808b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T09:17:38Z","title_canon_sha256":"e00792f31129d3eaf88791cff971f19d77529849f494355ac882984f79ffec0d"},"schema_version":"1.0","source":{"id":"2502.10735","kind":"arxiv","version":2}},"canonical_sha256":"a116df925ddd7a9fc9543db7cdd9393286b140e39165396ccaa487733e9f91a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a116df925ddd7a9fc9543db7cdd9393286b140e39165396ccaa487733e9f91a5","first_computed_at":"2026-07-05T11:08:16.420897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:16.420897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rdeCZvHMmw7cZtWFhr02+o7iOadqRVIwc89apgcLI0aMCoNCuIn+CVK2d5rQMQrs0GcTl2pur+9kx36xGq2ACA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:16.421428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10735","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:407e952d3d26443c600c46986544ca743366a5818699b9df8d4b2fa579d9284d","sha256:1c991065f615c233e4e33b71933354f947f586a73b987699d37f23791a5802ec"],"state_sha256":"34a1c0df3404a1671bc78a4838a723806021bf4d73cff2c335f547995d694597"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjR1iqCoQcuwH7NkZdwhtzAN09FQDjREnv8ANeN0IzMGYqUVqqAq8zmBucY/UYpqhj8OLlt4MuP8nuP4OFIEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T19:16:49.339782Z","bundle_sha256":"c665dcec218efae56ea6ac4b13134649fb1c3295d3f9d3cc3bd392b08f0f294c"}}