{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6SOXBQCWATYEH4SOKZBRL6MGAI","short_pith_number":"pith:6SOXBQCW","canonical_record":{"source":{"id":"2505.22689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T03:01:28Z","cross_cats_sorted":[],"title_canon_sha256":"c9abdf07e7e7a1a497f7c6417f34281b01e8734f04b894a8942927f35c9209df","abstract_canon_sha256":"c89717e23bc50f78bcc107db786180387648c00ecc296b770c0a675292336657"},"schema_version":"1.0"},"canonical_sha256":"f49d70c05604f043f24e564315f986021f16b75933c1e7d02be5fd23eb5fbbf1","source":{"kind":"arxiv","id":"2505.22689","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22689","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22689v1","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22689","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"pith_short_12","alias_value":"6SOXBQCWATYE","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"pith_short_16","alias_value":"6SOXBQCWATYEH4SO","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"pith_short_8","alias_value":"6SOXBQCW","created_at":"2026-07-05T11:11:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6SOXBQCWATYEH4SOKZBRL6MGAI","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T03:01:28Z","cross_cats_sorted":[],"title_canon_sha256":"c9abdf07e7e7a1a497f7c6417f34281b01e8734f04b894a8942927f35c9209df","abstract_canon_sha256":"c89717e23bc50f78bcc107db786180387648c00ecc296b770c0a675292336657"},"schema_version":"1.0"},"canonical_sha256":"f49d70c05604f043f24e564315f986021f16b75933c1e7d02be5fd23eb5fbbf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:48.624124Z","signature_b64":"1xauM6nJ01hkttSCldQb+nmkpCAbZj+U6SQoAVTrVDRbRssDK71xCxhERpxBBgr9hg2cjKWpkaQDQXcy4YhnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f49d70c05604f043f24e564315f986021f16b75933c1e7d02be5fd23eb5fbbf1","last_reissued_at":"2026-07-05T11:11:48.623625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:48.623625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22689","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yt/UDkXB2iTc8evITbJcT2O6FYXjNPDod1fG228CMaSLM5bZGz3sO/FPJVf5NcWtHgepfp2ayTe1n//D5KiFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:31:36.093400Z"},"content_sha256":"0a9e5a82e45ff15518b920a4952e9198fe3bf9da0630d79adefadd90b56c320a","schema_version":"1.0","event_id":"sha256:0a9e5a82e45ff15518b920a4952e9198fe3bf9da0630d79adefadd90b56c320a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6SOXBQCWATYEH4SOKZBRL6MGAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SlimLLM: Accurate Structured Pruning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jialong Guo, Xinghao Chen, Yehui Tang, Yunhe Wang","submitted_at":"2025-05-28T03:01:28Z","abstract_excerpt":"Large language models(LLMs) have garnered significant attention and demonstrated impressive capabilities in a wide range of applications. However, due to their enormous computational costs, the deployment and application of LLMs are often severely limited. To address this issue, structured pruning is an effective solution to compress the parameters of LLMs. Determining the importance of each sub-module in LLMs and minimizing performance loss are critical issues that need to be carefully addressed in structured pruning. In this paper, we propose an effective and fast structured pruning method n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22689","kind":"arxiv","version":1},"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/2505.22689/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":"2026-07-05T11:11:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mU4AGAOg9bBmdooJAZeOtbWTme9FF05LpGDQQMlxZu1JOo/WdqwzDVm0fApXlzc03SFXjrwGMLhbaqVteQVWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:31:36.093911Z"},"content_sha256":"1161e6a5736e535cbf01db653d500b0e47347b75367c7ad44751877174b4853f","schema_version":"1.0","event_id":"sha256:1161e6a5736e535cbf01db653d500b0e47347b75367c7ad44751877174b4853f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SOXBQCWATYEH4SOKZBRL6MGAI/bundle.json","state_url":"https://pith.science/pith/6SOXBQCWATYEH4SOKZBRL6MGAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SOXBQCWATYEH4SOKZBRL6MGAI/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":"2026-08-09T05:31:36Z","links":{"resolver":"https://pith.science/pith/6SOXBQCWATYEH4SOKZBRL6MGAI","bundle":"https://pith.science/pith/6SOXBQCWATYEH4SOKZBRL6MGAI/bundle.json","state":"https://pith.science/pith/6SOXBQCWATYEH4SOKZBRL6MGAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SOXBQCWATYEH4SOKZBRL6MGAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6SOXBQCWATYEH4SOKZBRL6MGAI","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":"c89717e23bc50f78bcc107db786180387648c00ecc296b770c0a675292336657","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T03:01:28Z","title_canon_sha256":"c9abdf07e7e7a1a497f7c6417f34281b01e8734f04b894a8942927f35c9209df"},"schema_version":"1.0","source":{"id":"2505.22689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22689","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22689v1","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22689","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"pith_short_12","alias_value":"6SOXBQCWATYE","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"pith_short_16","alias_value":"6SOXBQCWATYEH4SO","created_at":"2026-07-05T11:11:48Z"},{"alias_kind":"pith_short_8","alias_value":"6SOXBQCW","created_at":"2026-07-05T11:11:48Z"}],"graph_snapshots":[{"event_id":"sha256:1161e6a5736e535cbf01db653d500b0e47347b75367c7ad44751877174b4853f","target":"graph","created_at":"2026-07-05T11:11:48Z","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/2505.22689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models(LLMs) have garnered significant attention and demonstrated impressive capabilities in a wide range of applications. However, due to their enormous computational costs, the deployment and application of LLMs are often severely limited. To address this issue, structured pruning is an effective solution to compress the parameters of LLMs. Determining the importance of each sub-module in LLMs and minimizing performance loss are critical issues that need to be carefully addressed in structured pruning. In this paper, we propose an effective and fast structured pruning method n","authors_text":"Jialong Guo, Xinghao Chen, Yehui Tang, Yunhe Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T03:01:28Z","title":"SlimLLM: Accurate Structured Pruning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22689","kind":"arxiv","version":1},"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":"sha256:0a9e5a82e45ff15518b920a4952e9198fe3bf9da0630d79adefadd90b56c320a","target":"record","created_at":"2026-07-05T11:11:48Z","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":"c89717e23bc50f78bcc107db786180387648c00ecc296b770c0a675292336657","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T03:01:28Z","title_canon_sha256":"c9abdf07e7e7a1a497f7c6417f34281b01e8734f04b894a8942927f35c9209df"},"schema_version":"1.0","source":{"id":"2505.22689","kind":"arxiv","version":1}},"canonical_sha256":"f49d70c05604f043f24e564315f986021f16b75933c1e7d02be5fd23eb5fbbf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f49d70c05604f043f24e564315f986021f16b75933c1e7d02be5fd23eb5fbbf1","first_computed_at":"2026-07-05T11:11:48.623625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:48.623625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1xauM6nJ01hkttSCldQb+nmkpCAbZj+U6SQoAVTrVDRbRssDK71xCxhERpxBBgr9hg2cjKWpkaQDQXcy4YhnAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:48.624124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a9e5a82e45ff15518b920a4952e9198fe3bf9da0630d79adefadd90b56c320a","sha256:1161e6a5736e535cbf01db653d500b0e47347b75367c7ad44751877174b4853f"],"state_sha256":"d83f9dc8ee4a9268b222f2b98d8cb909c5709d5c6a74be1e25ed2e793f5ba507"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pgtaE94m3Gy5k3gaW0y6G2qcA15epFupVUSoR9P4KQVxQjA6z/CV2t5fV3Kp+iUnui4JRePyMLB8hcU3dByUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:31:36.098717Z","bundle_sha256":"e606f2a0cdebf239ceb7cca14db5b6245781a36dc6c82d84079e12d16907711e"}}