{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TQAU37W3NC3KWCVMEV646PP4UJ","short_pith_number":"pith:TQAU37W3","canonical_record":{"source":{"id":"2311.04902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T18:59:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c98819af906069b200191e7c78fd8d0661ee25e49d62026e2a724e304e79ea6","abstract_canon_sha256":"cc2cae1a8dc490150060852fcdd281e5f11cdec2e98defab986fa35db1f653a3"},"schema_version":"1.0"},"canonical_sha256":"9c014dfedb68b6ab0aac257dcf3dfca263930bde2640eb967ebdf52885693ece","source":{"kind":"arxiv","id":"2311.04902","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04902","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04902v2","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04902","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"TQAU37W3NC3K","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"TQAU37W3NC3KWCVM","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"TQAU37W3","created_at":"2026-07-05T08:05:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TQAU37W3NC3KWCVMEV646PP4UJ","target":"record","payload":{"canonical_record":{"source":{"id":"2311.04902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T18:59:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c98819af906069b200191e7c78fd8d0661ee25e49d62026e2a724e304e79ea6","abstract_canon_sha256":"cc2cae1a8dc490150060852fcdd281e5f11cdec2e98defab986fa35db1f653a3"},"schema_version":"1.0"},"canonical_sha256":"9c014dfedb68b6ab0aac257dcf3dfca263930bde2640eb967ebdf52885693ece","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:51.851437Z","signature_b64":"/1J0OfuYOrT9twliOVm3mAkiFQGjNmpnd/QAGfjbEjt1b9yxeXETBp1yPzFrlNJQrZ6LtA8Qd0zUVJaU7jKFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c014dfedb68b6ab0aac257dcf3dfca263930bde2640eb967ebdf52885693ece","last_reissued_at":"2026-07-05T08:05:51.851022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:51.851022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.04902","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":"2026-07-05T08:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Zyekhpk7Z9/vbogvkDxYfmv1bYGpZUNkNF/sZJ4UUabotg4s677voynDH4hDU84OVe4WwI0VCNhFEJ/3rkiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:43:31.008404Z"},"content_sha256":"0b4e73705dbbbeb79fc9abb76db0f2d68fb445dde9380a9cb1fc709f9e60e667","schema_version":"1.0","event_id":"sha256:0b4e73705dbbbeb79fc9abb76db0f2d68fb445dde9380a9cb1fc709f9e60e667"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TQAU37W3NC3KWCVMEV646PP4UJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Liqun Ma, Mingjie Sun, Rocktim Jyoti Das, Zhiqiang Shen","submitted_at":"2023-11-08T18:59:54Z","abstract_excerpt":"Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, removing some model weights without hurting performance. Prior approaches such as magnitude pruning, SparseGPT, and Wanda, either concentrated solely on weights or integrated weights with activations for sparsity. However, they overlooked the informative gradients derived from pretrained LLMs. In this paper, we present a novel sparsity-centric pruning method for pretrained LLMs, termed Gradient-based Language Model Pruner (GBLM-Pruner). GBLM-Pruner leverages the first-order term of the Taylor expans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04902","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/2311.04902/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":"2026-07-05T08:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gxns0TtjY/4TKK/Fd0cxd/sJvFLXYoWwjO59iav7wMFJXtWg0VM00HxhsIyIQqJD3S2IZOc8sWxksWeHIyfcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:43:31.008924Z"},"content_sha256":"d0c482645978018487e35464aed8d8973b587ce78024b71e022ff7c9e34e3ce5","schema_version":"1.0","event_id":"sha256:d0c482645978018487e35464aed8d8973b587ce78024b71e022ff7c9e34e3ce5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQAU37W3NC3KWCVMEV646PP4UJ/bundle.json","state_url":"https://pith.science/pith/TQAU37W3NC3KWCVMEV646PP4UJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQAU37W3NC3KWCVMEV646PP4UJ/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":"2026-08-15T17:43:31Z","links":{"resolver":"https://pith.science/pith/TQAU37W3NC3KWCVMEV646PP4UJ","bundle":"https://pith.science/pith/TQAU37W3NC3KWCVMEV646PP4UJ/bundle.json","state":"https://pith.science/pith/TQAU37W3NC3KWCVMEV646PP4UJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQAU37W3NC3KWCVMEV646PP4UJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TQAU37W3NC3KWCVMEV646PP4UJ","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":"cc2cae1a8dc490150060852fcdd281e5f11cdec2e98defab986fa35db1f653a3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T18:59:54Z","title_canon_sha256":"9c98819af906069b200191e7c78fd8d0661ee25e49d62026e2a724e304e79ea6"},"schema_version":"1.0","source":{"id":"2311.04902","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04902","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04902v2","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04902","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"TQAU37W3NC3K","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"TQAU37W3NC3KWCVM","created_at":"2026-07-05T08:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"TQAU37W3","created_at":"2026-07-05T08:05:51Z"}],"graph_snapshots":[{"event_id":"sha256:d0c482645978018487e35464aed8d8973b587ce78024b71e022ff7c9e34e3ce5","target":"graph","created_at":"2026-07-05T08:05:51Z","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/2311.04902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, removing some model weights without hurting performance. Prior approaches such as magnitude pruning, SparseGPT, and Wanda, either concentrated solely on weights or integrated weights with activations for sparsity. However, they overlooked the informative gradients derived from pretrained LLMs. In this paper, we present a novel sparsity-centric pruning method for pretrained LLMs, termed Gradient-based Language Model Pruner (GBLM-Pruner). GBLM-Pruner leverages the first-order term of the Taylor expans","authors_text":"Liqun Ma, Mingjie Sun, Rocktim Jyoti Das, Zhiqiang Shen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T18:59:54Z","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04902","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":"sha256:0b4e73705dbbbeb79fc9abb76db0f2d68fb445dde9380a9cb1fc709f9e60e667","target":"record","created_at":"2026-07-05T08:05:51Z","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":"cc2cae1a8dc490150060852fcdd281e5f11cdec2e98defab986fa35db1f653a3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T18:59:54Z","title_canon_sha256":"9c98819af906069b200191e7c78fd8d0661ee25e49d62026e2a724e304e79ea6"},"schema_version":"1.0","source":{"id":"2311.04902","kind":"arxiv","version":2}},"canonical_sha256":"9c014dfedb68b6ab0aac257dcf3dfca263930bde2640eb967ebdf52885693ece","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c014dfedb68b6ab0aac257dcf3dfca263930bde2640eb967ebdf52885693ece","first_computed_at":"2026-07-05T08:05:51.851022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:51.851022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/1J0OfuYOrT9twliOVm3mAkiFQGjNmpnd/QAGfjbEjt1b9yxeXETBp1yPzFrlNJQrZ6LtA8Qd0zUVJaU7jKFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:51.851437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04902","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b4e73705dbbbeb79fc9abb76db0f2d68fb445dde9380a9cb1fc709f9e60e667","sha256:d0c482645978018487e35464aed8d8973b587ce78024b71e022ff7c9e34e3ce5"],"state_sha256":"7baa4c07efac547985a7948686ae37fde8a467ff000f9ccb7ca0632d146e19fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"37UgMvByhXXJrmW5NrrRtx45MP7fuPzADWo3E91H0s4T6yUL9iVPhIeKLBi7YFNijtx2H8NnOUu8YnDZwuNVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:43:31.014522Z","bundle_sha256":"ec2c685e87c9ab5a22d4864c0bd672d7fc32837fbefbb12936f2fdc87a14bdce"}}