{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YHCSDGTG5TCON25TWWFD6CGPEM","short_pith_number":"pith:YHCSDGTG","canonical_record":{"source":{"id":"2506.08436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T04:19:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"38a2da5d4ef8382ce2c3ec656fe076fa8e7d0abc122337fc52b39709f495c9ff","abstract_canon_sha256":"518a281ad3435b8801d6a966e6481647f0bfaef68e6d338e884f36ce643b37e9"},"schema_version":"1.0"},"canonical_sha256":"c1c5219a66ecc4e6ebb3b58a3f08cf23061c6e82f3648168f1c03833546324c6","source":{"kind":"arxiv","id":"2506.08436","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08436","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08436v1","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08436","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_12","alias_value":"YHCSDGTG5TCO","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_16","alias_value":"YHCSDGTG5TCON25T","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_8","alias_value":"YHCSDGTG","created_at":"2026-07-05T11:18:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YHCSDGTG5TCON25TWWFD6CGPEM","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T04:19:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"38a2da5d4ef8382ce2c3ec656fe076fa8e7d0abc122337fc52b39709f495c9ff","abstract_canon_sha256":"518a281ad3435b8801d6a966e6481647f0bfaef68e6d338e884f36ce643b37e9"},"schema_version":"1.0"},"canonical_sha256":"c1c5219a66ecc4e6ebb3b58a3f08cf23061c6e82f3648168f1c03833546324c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:49.468404Z","signature_b64":"vsxgK3EyUgrJxtbfHgDuABl/6naB2n0yLLbcVkDKUf097L0BTgIOdtffbtqEf6gYtn4Jy229ZddLG9SZ/YJoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1c5219a66ecc4e6ebb3b58a3f08cf23061c6e82f3648168f1c03833546324c6","last_reissued_at":"2026-07-05T11:18:49.467931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:49.467931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08436","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":"2026-07-05T11:18:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WuRGwGf5FHyJokb55qU/4jLIUfILhUAUmiu+uaJ2NAyxJ05ojAOq5lRXtM+Z0YWymZ0O20JPNleVIBZ6a9FhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:08:49.592807Z"},"content_sha256":"c71a4939ed12875adfdcc97cfa2d40c0539dd04823a3166c550c77cddf68b1a3","schema_version":"1.0","event_id":"sha256:c71a4939ed12875adfdcc97cfa2d40c0539dd04823a3166c550c77cddf68b1a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YHCSDGTG5TCON25TWWFD6CGPEM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Olica: Efficient Structured Pruning of Large Language Models without Retraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Huazhen Lin, Jiujun He","submitted_at":"2025-06-10T04:19:38Z","abstract_excerpt":"Most existing structured pruning methods for Large Language Models (LLMs) require substantial computational and data resources for retraining to reestablish the corrupted correlations, making them prohibitively expensive. To address this, we propose a pruning framework for LLMs called Orthogonal decomposition and Linear Calibration (Olica), which eliminates the need for retraining. A key observation is that the multi-head attention (MHA) layer depends on two types of matrix products. By treating these matrix products as unified entities and applying principal component analysis (PCA), we extra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08436","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/2506.08436/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":"2026-07-05T11:18:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8OXzf/Pd9PqqhqvD09BwpvjNWp4fl3km+f3vKH2nkaNufd5bimrucbD2uvQ1gMukk+KHkXBYSFDiwBp6qlBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:08:49.593501Z"},"content_sha256":"23e92ab848fd6d752a395a3cc1cf9c27e7fc1c25d334b11049ed00b65e52dd6b","schema_version":"1.0","event_id":"sha256:23e92ab848fd6d752a395a3cc1cf9c27e7fc1c25d334b11049ed00b65e52dd6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YHCSDGTG5TCON25TWWFD6CGPEM/bundle.json","state_url":"https://pith.science/pith/YHCSDGTG5TCON25TWWFD6CGPEM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YHCSDGTG5TCON25TWWFD6CGPEM/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":"2026-08-08T06:08:49Z","links":{"resolver":"https://pith.science/pith/YHCSDGTG5TCON25TWWFD6CGPEM","bundle":"https://pith.science/pith/YHCSDGTG5TCON25TWWFD6CGPEM/bundle.json","state":"https://pith.science/pith/YHCSDGTG5TCON25TWWFD6CGPEM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YHCSDGTG5TCON25TWWFD6CGPEM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YHCSDGTG5TCON25TWWFD6CGPEM","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":"518a281ad3435b8801d6a966e6481647f0bfaef68e6d338e884f36ce643b37e9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T04:19:38Z","title_canon_sha256":"38a2da5d4ef8382ce2c3ec656fe076fa8e7d0abc122337fc52b39709f495c9ff"},"schema_version":"1.0","source":{"id":"2506.08436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08436","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08436v1","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08436","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_12","alias_value":"YHCSDGTG5TCO","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_16","alias_value":"YHCSDGTG5TCON25T","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_8","alias_value":"YHCSDGTG","created_at":"2026-07-05T11:18:49Z"}],"graph_snapshots":[{"event_id":"sha256:23e92ab848fd6d752a395a3cc1cf9c27e7fc1c25d334b11049ed00b65e52dd6b","target":"graph","created_at":"2026-07-05T11:18:49Z","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/2506.08436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing structured pruning methods for Large Language Models (LLMs) require substantial computational and data resources for retraining to reestablish the corrupted correlations, making them prohibitively expensive. To address this, we propose a pruning framework for LLMs called Orthogonal decomposition and Linear Calibration (Olica), which eliminates the need for retraining. A key observation is that the multi-head attention (MHA) layer depends on two types of matrix products. By treating these matrix products as unified entities and applying principal component analysis (PCA), we extra","authors_text":"Huazhen Lin, Jiujun He","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T04:19:38Z","title":"Olica: Efficient Structured Pruning of Large Language Models without Retraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08436","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:c71a4939ed12875adfdcc97cfa2d40c0539dd04823a3166c550c77cddf68b1a3","target":"record","created_at":"2026-07-05T11:18:49Z","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":"518a281ad3435b8801d6a966e6481647f0bfaef68e6d338e884f36ce643b37e9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T04:19:38Z","title_canon_sha256":"38a2da5d4ef8382ce2c3ec656fe076fa8e7d0abc122337fc52b39709f495c9ff"},"schema_version":"1.0","source":{"id":"2506.08436","kind":"arxiv","version":1}},"canonical_sha256":"c1c5219a66ecc4e6ebb3b58a3f08cf23061c6e82f3648168f1c03833546324c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1c5219a66ecc4e6ebb3b58a3f08cf23061c6e82f3648168f1c03833546324c6","first_computed_at":"2026-07-05T11:18:49.467931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:49.467931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vsxgK3EyUgrJxtbfHgDuABl/6naB2n0yLLbcVkDKUf097L0BTgIOdtffbtqEf6gYtn4Jy229ZddLG9SZ/YJoCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:49.468404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c71a4939ed12875adfdcc97cfa2d40c0539dd04823a3166c550c77cddf68b1a3","sha256:23e92ab848fd6d752a395a3cc1cf9c27e7fc1c25d334b11049ed00b65e52dd6b"],"state_sha256":"4d404449881a1e1c64bba5afd5aba23dbe04dca4a9733b9362c0bd0f796f6e85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfqjCF+ASPtaYKPQK4jpb/dPdwNRcVVA24TSOB/i64Ecm8oUxapKWzsTur9z97U9H6jE75gpSf9POfQWfC0YBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:08:49.599689Z","bundle_sha256":"86d557adefafc1f0db3a1755cd2be2632ee2104836623404b0d57b7285aeb88e"}}