{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BP3QDX6Y356FERIX7WSZGEWBYX","short_pith_number":"pith:BP3QDX6Y","canonical_record":{"source":{"id":"2511.15390","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-19T12:38:21Z","cross_cats_sorted":[],"title_canon_sha256":"262b396c2f5ece336af1347458ced419361caf846502d10cc4e449d9521e8a68","abstract_canon_sha256":"b28c8842876bd5afa570dd622e4d404bc5953e15f385e65d5394e6b5ba3c3d3c"},"schema_version":"1.0"},"canonical_sha256":"0bf701dfd8df7c524517fda59312c1c5db4e78435dea062b5bbafb7768268753","source":{"kind":"arxiv","id":"2511.15390","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.15390","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2511.15390v2","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.15390","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"BP3QDX6Y356F","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"BP3QDX6Y356FERIX","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"BP3QDX6Y","created_at":"2026-05-28T02:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BP3QDX6Y356FERIX7WSZGEWBYX","target":"record","payload":{"canonical_record":{"source":{"id":"2511.15390","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-19T12:38:21Z","cross_cats_sorted":[],"title_canon_sha256":"262b396c2f5ece336af1347458ced419361caf846502d10cc4e449d9521e8a68","abstract_canon_sha256":"b28c8842876bd5afa570dd622e4d404bc5953e15f385e65d5394e6b5ba3c3d3c"},"schema_version":"1.0"},"canonical_sha256":"0bf701dfd8df7c524517fda59312c1c5db4e78435dea062b5bbafb7768268753","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:44.420415Z","signature_b64":"WznAlNYuxq57LFtHl7xwVG+vuFGy6QlD+4wtKfnVraWu93De0vCWgc0IqyNacqGBZBW0rBdc5lgbO+C9Xq5iAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf701dfd8df7c524517fda59312c1c5db4e78435dea062b5bbafb7768268753","last_reissued_at":"2026-05-28T02:04:44.419716Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:44.419716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.15390","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":"2026-05-28T02:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"om/fWFsi6rC6gj8L517r7Ssif9GQ5cPCZHOcxpgpFvZl8OmpNE8xeoDb4t8ctSQGpxB+/u3vE7d+cXE5txOoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:50:31.468229Z"},"content_sha256":"029bd0d39b25d50585b0b050ef4239a2c86b41703d982662f090fe8bb0077069","schema_version":"1.0","event_id":"sha256:029bd0d39b25d50585b0b050ef4239a2c86b41703d982662f090fe8bb0077069"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BP3QDX6Y356FERIX7WSZGEWBYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Pruning Discovery for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enneng Yang, Haidong Kang, Hao Wang, Hongning Dai, Lihong Lin","submitted_at":"2025-11-19T12:38:21Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive size. Existing pruning methods (e.g., Wanda) tailored for LLMs rely heavily on manual design pruning algorithms, thereby leading to huge labor costs and requires expert knowledge. Furthermore, we are the first to identify the serious outlier value issue behind dramatic performance degradation under high pruning ratios that are caused by uniform sparsity, raising an additional concern about how to design adaptive pruning sparsity ideal for LLMs. Can LL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.15390","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/2511.15390/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":"2026-05-28T02:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ksg6YOWTUdskwYVQ1s1hcyQ0q4uFfEPlPpl4p964UBUpQkAQaIAOcXWVOGCprqsswsAh3xbt6b82dEE/MKZbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:50:31.468627Z"},"content_sha256":"0529ca5bbe70e3c0332985ce8c07886fd6104f852b9c5c1b21f4f72f605f9013","schema_version":"1.0","event_id":"sha256:0529ca5bbe70e3c0332985ce8c07886fd6104f852b9c5c1b21f4f72f605f9013"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BP3QDX6Y356FERIX7WSZGEWBYX/bundle.json","state_url":"https://pith.science/pith/BP3QDX6Y356FERIX7WSZGEWBYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BP3QDX6Y356FERIX7WSZGEWBYX/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":"2026-05-30T00:50:31Z","links":{"resolver":"https://pith.science/pith/BP3QDX6Y356FERIX7WSZGEWBYX","bundle":"https://pith.science/pith/BP3QDX6Y356FERIX7WSZGEWBYX/bundle.json","state":"https://pith.science/pith/BP3QDX6Y356FERIX7WSZGEWBYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BP3QDX6Y356FERIX7WSZGEWBYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BP3QDX6Y356FERIX7WSZGEWBYX","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":"b28c8842876bd5afa570dd622e4d404bc5953e15f385e65d5394e6b5ba3c3d3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-19T12:38:21Z","title_canon_sha256":"262b396c2f5ece336af1347458ced419361caf846502d10cc4e449d9521e8a68"},"schema_version":"1.0","source":{"id":"2511.15390","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.15390","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2511.15390v2","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.15390","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"BP3QDX6Y356F","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"BP3QDX6Y356FERIX","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"BP3QDX6Y","created_at":"2026-05-28T02:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:0529ca5bbe70e3c0332985ce8c07886fd6104f852b9c5c1b21f4f72f605f9013","target":"graph","created_at":"2026-05-28T02:04:44Z","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/2511.15390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive size. Existing pruning methods (e.g., Wanda) tailored for LLMs rely heavily on manual design pruning algorithms, thereby leading to huge labor costs and requires expert knowledge. Furthermore, we are the first to identify the serious outlier value issue behind dramatic performance degradation under high pruning ratios that are caused by uniform sparsity, raising an additional concern about how to design adaptive pruning sparsity ideal for LLMs. Can LL","authors_text":"Enneng Yang, Haidong Kang, Hao Wang, Hongning Dai, Lihong Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-19T12:38:21Z","title":"Automatic Pruning Discovery for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.15390","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":"sha256:029bd0d39b25d50585b0b050ef4239a2c86b41703d982662f090fe8bb0077069","target":"record","created_at":"2026-05-28T02:04:44Z","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":"b28c8842876bd5afa570dd622e4d404bc5953e15f385e65d5394e6b5ba3c3d3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-19T12:38:21Z","title_canon_sha256":"262b396c2f5ece336af1347458ced419361caf846502d10cc4e449d9521e8a68"},"schema_version":"1.0","source":{"id":"2511.15390","kind":"arxiv","version":2}},"canonical_sha256":"0bf701dfd8df7c524517fda59312c1c5db4e78435dea062b5bbafb7768268753","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf701dfd8df7c524517fda59312c1c5db4e78435dea062b5bbafb7768268753","first_computed_at":"2026-05-28T02:04:44.419716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:44.419716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WznAlNYuxq57LFtHl7xwVG+vuFGy6QlD+4wtKfnVraWu93De0vCWgc0IqyNacqGBZBW0rBdc5lgbO+C9Xq5iAQ==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:44.420415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.15390","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:029bd0d39b25d50585b0b050ef4239a2c86b41703d982662f090fe8bb0077069","sha256:0529ca5bbe70e3c0332985ce8c07886fd6104f852b9c5c1b21f4f72f605f9013"],"state_sha256":"f5b118e23c4ffbd2a0593a7d6f2ca47f62805c9485244a3ff3af5cbbbe69d2dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SEM8bfsMAnIcobhrCG8nIMOjIpqXfdQH+jw784tjfTWqamMts84BH2lezgNbV70q2nForQC9mXKCD8bGd0WyBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T00:50:31.470651Z","bundle_sha256":"c69769073e37946a3eb43149c8f75bfd102f6867ebde5a413f9494d8107336b2"}}