{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UUJI3VCD7C2B7TL7EFFQAJ6BIM","short_pith_number":"pith:UUJI3VCD","canonical_record":{"source":{"id":"2306.11695","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T17:18:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9b92b75b9a1fafea9f2ef9463f06a2857e2f8610d84409b6122816b94f657316","abstract_canon_sha256":"8bd7eefa2e525be9a8735c1df727f097e7d9a424979146ae0529209eab22af9e"},"schema_version":"1.0"},"canonical_sha256":"a5128dd443f8b41fcd7f214b0027c1432852a98772cd0d9ff07c4f85d33c8cbd","source":{"kind":"arxiv","id":"2306.11695","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11695","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11695v3","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11695","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"UUJI3VCD7C2B","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UUJI3VCD7C2B7TL7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UUJI3VCD","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UUJI3VCD7C2B7TL7EFFQAJ6BIM","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11695","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T17:18:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9b92b75b9a1fafea9f2ef9463f06a2857e2f8610d84409b6122816b94f657316","abstract_canon_sha256":"8bd7eefa2e525be9a8735c1df727f097e7d9a424979146ae0529209eab22af9e"},"schema_version":"1.0"},"canonical_sha256":"a5128dd443f8b41fcd7f214b0027c1432852a98772cd0d9ff07c4f85d33c8cbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.337163Z","signature_b64":"1DO01t+kNFYiimAF7CW+dfNqHLibUZ40OlsYIzo4lYbi52M4Lw9XXYtLQh9p8sTLLEd8MZ4u5EXVS1KaQ9wkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5128dd443f8b41fcd7f214b0027c1432852a98772cd0d9ff07c4f85d33c8cbd","last_reissued_at":"2026-05-17T23:38:47.336614Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.336614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11695","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/+ot00y3/r3mFt8aSe1Zh7UgiMH322B0BkkAgeQAZEPJGSF8146grBFB2T0FOfliJG8mFDgqRQ/HiJSmrpPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:18:57.575520Z"},"content_sha256":"2c6958854cf69797ae679be0e0f350f1f56f58c6043aac44c184793ecb6ee473","schema_version":"1.0","event_id":"sha256:2c6958854cf69797ae679be0e0f350f1f56f58c6043aac44c184793ecb6ee473"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UUJI3VCD7C2B7TL7EFFQAJ6BIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Simple and Effective Pruning Approach for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Wanda prunes large language models by removing weights whose magnitudes times input activations are smallest, with no retraining required.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Bair, J. Zico Kolter, Mingjie Sun, Zhuang Liu","submitted_at":"2023-06-20T17:18:20Z","abstract_excerpt":"As their size increases, Large Languages Models (LLMs) are natural candidates for network pruning methods: approaches that drop a subset of network weights while striving to preserve performance. Existing methods, however, require either retraining, which is rarely affordable for billion-scale LLMs, or solving a weight reconstruction problem reliant on second-order information, which may also be computationally expensive. In this paper, we introduce a novel, straightforward yet effective pruning method, termed Wanda (Pruning by Weights and activations), designed to induce sparsity in pretraine"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Wanda significantly outperforms the established baseline of magnitude pruning and performs competitively against recent methods involving intensive weight update on LLaMA and LLaMA-2 across various language benchmarks, with no retraining or weight update required.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The central assumption is that the product of weight magnitude and input activation reliably identifies weights whose removal will least affect model performance, motivated by emergent large-magnitude features but without a formal proof that this criterion is optimal or generalizes beyond the tested models.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Wanda prunes pretrained LLMs by dropping weights with smallest magnitude times activation values per output channel, with no retraining needed and better results than magnitude pruning on language benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Wanda prunes large language models by removing weights whose magnitudes times input activations are smallest, with no retraining required.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"71016ab615440db7754d7869f62659141955fc8c09bbc5ce2165b455abfe444f"},"source":{"id":"2306.11695","kind":"arxiv","version":3},"verdict":{"id":"7397a1c0-a27e-43f8-ac96-b7dd12a0aad6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T16:08:25.620116Z","strongest_claim":"Wanda significantly outperforms the established baseline of magnitude pruning and performs competitively against recent methods involving intensive weight update on LLaMA and LLaMA-2 across various language benchmarks, with no retraining or weight update required.","one_line_summary":"Wanda prunes pretrained LLMs by dropping weights with smallest magnitude times activation values per output channel, with no retraining needed and better results than magnitude pruning on language benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The central assumption is that the product of weight magnitude and input activation reliably identifies weights whose removal will least affect model performance, motivated by emergent large-magnitude features but without a formal proof that this criterion is optimal or generalizes beyond the tested models.","pith_extraction_headline":"Wanda prunes large language models by removing weights whose magnitudes times input activations are smallest, with no retraining required."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"068cdd3ac91ece8e10f3c596f5b95a706ee3ae5f90a5009f3368649bfbbe5656"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"7397a1c0-a27e-43f8-ac96-b7dd12a0aad6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wy7y3R5jkRflcxJ33xRwmIPNkI40Gqj0pJcZ3Ei+gyweAkrY7uri71tBdXvtVHorIiTxeQ1lKjpHwgNiqBLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:18:57.576370Z"},"content_sha256":"34aca5acd1128d7fe5f0b725054405cbe630ba82fa2f76195c7d2735a537fa56","schema_version":"1.0","event_id":"sha256:34aca5acd1128d7fe5f0b725054405cbe630ba82fa2f76195c7d2735a537fa56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUJI3VCD7C2B7TL7EFFQAJ6BIM/bundle.json","state_url":"https://pith.science/pith/UUJI3VCD7C2B7TL7EFFQAJ6BIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUJI3VCD7C2B7TL7EFFQAJ6BIM/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":"2026-05-21T22:18:57Z","links":{"resolver":"https://pith.science/pith/UUJI3VCD7C2B7TL7EFFQAJ6BIM","bundle":"https://pith.science/pith/UUJI3VCD7C2B7TL7EFFQAJ6BIM/bundle.json","state":"https://pith.science/pith/UUJI3VCD7C2B7TL7EFFQAJ6BIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUJI3VCD7C2B7TL7EFFQAJ6BIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UUJI3VCD7C2B7TL7EFFQAJ6BIM","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":"8bd7eefa2e525be9a8735c1df727f097e7d9a424979146ae0529209eab22af9e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T17:18:20Z","title_canon_sha256":"9b92b75b9a1fafea9f2ef9463f06a2857e2f8610d84409b6122816b94f657316"},"schema_version":"1.0","source":{"id":"2306.11695","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11695","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11695v3","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11695","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"UUJI3VCD7C2B","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UUJI3VCD7C2B7TL7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UUJI3VCD","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:34aca5acd1128d7fe5f0b725054405cbe630ba82fa2f76195c7d2735a537fa56","target":"graph","created_at":"2026-05-17T23:38:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Wanda significantly outperforms the established baseline of magnitude pruning and performs competitively against recent methods involving intensive weight update on LLaMA and LLaMA-2 across various language benchmarks, with no retraining or weight update required."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The central assumption is that the product of weight magnitude and input activation reliably identifies weights whose removal will least affect model performance, motivated by emergent large-magnitude features but without a formal proof that this criterion is optimal or generalizes beyond the tested models."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Wanda prunes pretrained LLMs by dropping weights with smallest magnitude times activation values per output channel, with no retraining needed and better results than magnitude pruning on language benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Wanda prunes large language models by removing weights whose magnitudes times input activations are smallest, with no retraining required."}],"snapshot_sha256":"71016ab615440db7754d7869f62659141955fc8c09bbc5ce2165b455abfe444f"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"068cdd3ac91ece8e10f3c596f5b95a706ee3ae5f90a5009f3368649bfbbe5656"},"paper":{"abstract_excerpt":"As their size increases, Large Languages Models (LLMs) are natural candidates for network pruning methods: approaches that drop a subset of network weights while striving to preserve performance. Existing methods, however, require either retraining, which is rarely affordable for billion-scale LLMs, or solving a weight reconstruction problem reliant on second-order information, which may also be computationally expensive. In this paper, we introduce a novel, straightforward yet effective pruning method, termed Wanda (Pruning by Weights and activations), designed to induce sparsity in pretraine","authors_text":"Anna Bair, J. Zico Kolter, Mingjie Sun, Zhuang Liu","cross_cats":["cs.AI","cs.LG"],"headline":"Wanda prunes large language models by removing weights whose magnitudes times input activations are smallest, with no retraining required.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T17:18:20Z","title":"A Simple and Effective Pruning Approach for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11695","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T16:08:25.620116Z","id":"7397a1c0-a27e-43f8-ac96-b7dd12a0aad6","model_set":{"reader":"grok-4.3"},"one_line_summary":"Wanda prunes pretrained LLMs by dropping weights with smallest magnitude times activation values per output channel, with no retraining needed and better results than magnitude pruning on language benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Wanda prunes large language models by removing weights whose magnitudes times input activations are smallest, with no retraining required.","strongest_claim":"Wanda significantly outperforms the established baseline of magnitude pruning and performs competitively against recent methods involving intensive weight update on LLaMA and LLaMA-2 across various language benchmarks, with no retraining or weight update required.","weakest_assumption":"The central assumption is that the product of weight magnitude and input activation reliably identifies weights whose removal will least affect model performance, motivated by emergent large-magnitude features but without a formal proof that this criterion is optimal or generalizes beyond the tested models."}},"verdict_id":"7397a1c0-a27e-43f8-ac96-b7dd12a0aad6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2c6958854cf69797ae679be0e0f350f1f56f58c6043aac44c184793ecb6ee473","target":"record","created_at":"2026-05-17T23:38:47Z","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":"8bd7eefa2e525be9a8735c1df727f097e7d9a424979146ae0529209eab22af9e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T17:18:20Z","title_canon_sha256":"9b92b75b9a1fafea9f2ef9463f06a2857e2f8610d84409b6122816b94f657316"},"schema_version":"1.0","source":{"id":"2306.11695","kind":"arxiv","version":3}},"canonical_sha256":"a5128dd443f8b41fcd7f214b0027c1432852a98772cd0d9ff07c4f85d33c8cbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5128dd443f8b41fcd7f214b0027c1432852a98772cd0d9ff07c4f85d33c8cbd","first_computed_at":"2026-05-17T23:38:47.336614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.336614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1DO01t+kNFYiimAF7CW+dfNqHLibUZ40OlsYIzo4lYbi52M4Lw9XXYtLQh9p8sTLLEd8MZ4u5EXVS1KaQ9wkAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.337163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11695","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c6958854cf69797ae679be0e0f350f1f56f58c6043aac44c184793ecb6ee473","sha256:34aca5acd1128d7fe5f0b725054405cbe630ba82fa2f76195c7d2735a537fa56"],"state_sha256":"ec249ef34ec03918ea7bad74c67388e17791be8b7101240df3ab4d4e77c46df5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXoGoMRFjJjIA/azE2Rovu9lZycDosxx82Kzdl9MkfQPxW+VtLmQPgTcs9FJe5Ap+AADa2FprE73Z1nxyr+LCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T22:18:57.579976Z","bundle_sha256":"accd4146764d5fda92905f39efdf167da5d12b5726ca4cee1cc48968e4b6c48e"}}