{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BG36LJ57J6UJ5BBQFSP3VINZGX","short_pith_number":"pith:BG36LJ57","canonical_record":{"source":{"id":"2310.05175","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-08T14:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"f89258b47cf544b7166366777e8ec5e2eab8f3a35e6747143da6b86e36021a8e","abstract_canon_sha256":"2759277e6c6f859f2d05f7d5843d2cb5daa7c9459908ff4529f9ff194e9695c3"},"schema_version":"1.0"},"canonical_sha256":"09b7e5a7bf4fa89e84302c9fbaa1b935d5451f24bd8c47a711b28d6ebd5bfcee","source":{"kind":"arxiv","id":"2310.05175","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05175","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05175v4","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05175","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_12","alias_value":"BG36LJ57J6UJ","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_16","alias_value":"BG36LJ57J6UJ5BBQ","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_8","alias_value":"BG36LJ57","created_at":"2026-07-05T11:29:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BG36LJ57J6UJ5BBQFSP3VINZGX","target":"record","payload":{"canonical_record":{"source":{"id":"2310.05175","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-08T14:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"f89258b47cf544b7166366777e8ec5e2eab8f3a35e6747143da6b86e36021a8e","abstract_canon_sha256":"2759277e6c6f859f2d05f7d5843d2cb5daa7c9459908ff4529f9ff194e9695c3"},"schema_version":"1.0"},"canonical_sha256":"09b7e5a7bf4fa89e84302c9fbaa1b935d5451f24bd8c47a711b28d6ebd5bfcee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:46.476709Z","signature_b64":"Z1grXddVu4nUaYctjfOtAduYbPwI3XJHbNN+obVW1+GzldKsgnJfGu80ZmMc5iSSENPTT5fQvmq94seLPQXJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09b7e5a7bf4fa89e84302c9fbaa1b935d5451f24bd8c47a711b28d6ebd5bfcee","last_reissued_at":"2026-07-05T11:29:46.476282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:46.476282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.05175","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Op8uU3/hn5xAoPkFKYVvqPEVJUY3cEh7K2pJVHxGrVxx4M2ihbVD2hfAP/eibeyhn5Qns5K54ZsP95Y8LQoZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:49:01.145601Z"},"content_sha256":"e44099bf5e206065bd9db2fc4fc47efc6b39f2893262fd4354362cda142951ae","schema_version":"1.0","event_id":"sha256:e44099bf5e206065bd9db2fc4fc47efc6b39f2893262fd4354362cda142951ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BG36LJ57J6UJ5BBQFSP3VINZGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ajay Jaiswal, Cheng-Yu Hsieh, Gen Li, Lu Yin, Michael Bendersky, Mykola Pechenizkiy, Shiwei Liu, Yaqing Wang, Yi Liang, Yiling Jia, You Wu, Zhangyang Wang, Zhenyu Zhang","submitted_at":"2023-10-08T14:22:58Z","abstract_excerpt":"Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge when it comes to practical deployment due to their colossal model size. In response to this challenge, efforts have been directed toward the application of traditional network pruning techniques to LLMs, uncovering a massive number of parameters that can be pruned in one-shot without hurting performance. Prevailing LLM pruning strategies have consistently adhered to the practice of uniformly pruning all layers at equivalent sparsity, resulting in robust performance. However, this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05175","kind":"arxiv","version":4},"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/2310.05175/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":"2026-07-05T11:29:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v6gmeO3B/ryYL1sFVDiTacTWtPyCG1XcizIbqPlgmbG9jPFuAZ49FGZN1hF+3vSw7vi7+hEOxzt1BgDxrbtzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:49:01.145975Z"},"content_sha256":"fa045b72880f223d1684dfd44b054659265af31f5ab94fe54abc6630377ab121","schema_version":"1.0","event_id":"sha256:fa045b72880f223d1684dfd44b054659265af31f5ab94fe54abc6630377ab121"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BG36LJ57J6UJ5BBQFSP3VINZGX/bundle.json","state_url":"https://pith.science/pith/BG36LJ57J6UJ5BBQFSP3VINZGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BG36LJ57J6UJ5BBQFSP3VINZGX/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":"2026-08-18T08:49:01Z","links":{"resolver":"https://pith.science/pith/BG36LJ57J6UJ5BBQFSP3VINZGX","bundle":"https://pith.science/pith/BG36LJ57J6UJ5BBQFSP3VINZGX/bundle.json","state":"https://pith.science/pith/BG36LJ57J6UJ5BBQFSP3VINZGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BG36LJ57J6UJ5BBQFSP3VINZGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BG36LJ57J6UJ5BBQFSP3VINZGX","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":"2759277e6c6f859f2d05f7d5843d2cb5daa7c9459908ff4529f9ff194e9695c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-08T14:22:58Z","title_canon_sha256":"f89258b47cf544b7166366777e8ec5e2eab8f3a35e6747143da6b86e36021a8e"},"schema_version":"1.0","source":{"id":"2310.05175","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05175","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05175v4","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05175","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_12","alias_value":"BG36LJ57J6UJ","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_16","alias_value":"BG36LJ57J6UJ5BBQ","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_8","alias_value":"BG36LJ57","created_at":"2026-07-05T11:29:46Z"}],"graph_snapshots":[{"event_id":"sha256:fa045b72880f223d1684dfd44b054659265af31f5ab94fe54abc6630377ab121","target":"graph","created_at":"2026-07-05T11:29:46Z","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/2310.05175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge when it comes to practical deployment due to their colossal model size. In response to this challenge, efforts have been directed toward the application of traditional network pruning techniques to LLMs, uncovering a massive number of parameters that can be pruned in one-shot without hurting performance. Prevailing LLM pruning strategies have consistently adhered to the practice of uniformly pruning all layers at equivalent sparsity, resulting in robust performance. However, this","authors_text":"Ajay Jaiswal, Cheng-Yu Hsieh, Gen Li, Lu Yin, Michael Bendersky, Mykola Pechenizkiy, Shiwei Liu, Yaqing Wang, Yi Liang, Yiling Jia, You Wu, Zhangyang Wang, Zhenyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-08T14:22:58Z","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05175","kind":"arxiv","version":4},"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:e44099bf5e206065bd9db2fc4fc47efc6b39f2893262fd4354362cda142951ae","target":"record","created_at":"2026-07-05T11:29:46Z","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":"2759277e6c6f859f2d05f7d5843d2cb5daa7c9459908ff4529f9ff194e9695c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-08T14:22:58Z","title_canon_sha256":"f89258b47cf544b7166366777e8ec5e2eab8f3a35e6747143da6b86e36021a8e"},"schema_version":"1.0","source":{"id":"2310.05175","kind":"arxiv","version":4}},"canonical_sha256":"09b7e5a7bf4fa89e84302c9fbaa1b935d5451f24bd8c47a711b28d6ebd5bfcee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09b7e5a7bf4fa89e84302c9fbaa1b935d5451f24bd8c47a711b28d6ebd5bfcee","first_computed_at":"2026-07-05T11:29:46.476282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:46.476282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z1grXddVu4nUaYctjfOtAduYbPwI3XJHbNN+obVW1+GzldKsgnJfGu80ZmMc5iSSENPTT5fQvmq94seLPQXJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:46.476709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05175","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e44099bf5e206065bd9db2fc4fc47efc6b39f2893262fd4354362cda142951ae","sha256:fa045b72880f223d1684dfd44b054659265af31f5ab94fe54abc6630377ab121"],"state_sha256":"1690276919bca6e975a139020b65c53b6d96b9943f3153f37a6032e630749f5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNbYQcf+H1sOjH4A3elmM6Fe9mmp50ouN9hN1y308mYsHefZZg9ZpTyb8SfVs2QHqbyDyXo2JuzlCa02EyUXAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:49:01.148584Z","bundle_sha256":"029f63a290a2b1da228b42b5fe0c82ae3e81174f73b3d101bd2418e1c2e28654"}}