{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XBWBH3ZDC6WHZLTBHTPB462CFV","short_pith_number":"pith:XBWBH3ZD","canonical_record":{"source":{"id":"2505.20155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"e696905241e2b89550a90afddf411417a42be38578cd63612d4d8e0c93e35d7d","abstract_canon_sha256":"2c0e9fc7e16abc6eb8cfb7b176cb729d81b0cca970da22d7a2e32ca2742250eb"},"schema_version":"1.0"},"canonical_sha256":"b86c13ef2317ac7cae613cde1e7b422d6417836e2790774271f3d373f9580f52","source":{"kind":"arxiv","id":"2505.20155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20155","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20155v1","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20155","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"XBWBH3ZDC6WH","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"XBWBH3ZDC6WHZLTB","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"XBWBH3ZD","created_at":"2026-07-05T11:09:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XBWBH3ZDC6WHZLTBHTPB462CFV","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"e696905241e2b89550a90afddf411417a42be38578cd63612d4d8e0c93e35d7d","abstract_canon_sha256":"2c0e9fc7e16abc6eb8cfb7b176cb729d81b0cca970da22d7a2e32ca2742250eb"},"schema_version":"1.0"},"canonical_sha256":"b86c13ef2317ac7cae613cde1e7b422d6417836e2790774271f3d373f9580f52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:53.437482Z","signature_b64":"gdsiPuNfmUkEVSkbVJpwGBiZaL+sjwgMcOf7EO/vCdjE53Uonknqw6hBO7h0fNDXZMyA36tlsqBDniK+p10NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b86c13ef2317ac7cae613cde1e7b422d6417836e2790774271f3d373f9580f52","last_reissued_at":"2026-07-05T11:09:53.436891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:53.436891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20155","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":"2026-07-05T11:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LVnLY6vduCARhg9OFpjsgp6Nax0NWuiTN9sZdCMOrPLJGNGZXW0QdYVljSlkICHEPUiOq5mzqrH5p8AEkbUbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:22:04.071598Z"},"content_sha256":"92cc3f4aa9afd7257e2e6c4206d8cc1862fca768df3a3f7301cd98cd0d78cae3","schema_version":"1.0","event_id":"sha256:92cc3f4aa9afd7257e2e6c4206d8cc1862fca768df3a3f7301cd98cd0d78cae3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XBWBH3ZDC6WHZLTBHTPB462CFV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Chen, Fisher Yu, Hanting Chen, Huiling Zhen, Jialong Guo, Jiarui Qin, Jinpeng Li, Meng Zhang, Rongju Ruan, Ruiming Tang, Tao Yuan, Xiaojun Meng, Xinghao Chen, Yasheng Wang, Yehui Tang, Yichun Yin, Yunhe Wang (and Other Contributors), Zheyuan Bai","submitted_at":"2025-05-26T15:57:08Z","abstract_excerpt":"Large Language Models (LLMs) deliver state-of-the-art capabilities across numerous tasks, but their immense size and inference costs pose significant computational challenges for practical deployment. While structured pruning offers a promising avenue for model compression, existing methods often struggle with the detrimental effects of aggressive, simultaneous width and depth reductions, leading to substantial performance degradation. This paper argues that a critical, often overlooked, aspect in making such aggressive joint pruning viable is the strategic re-initialization and adjustment of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20155","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/2505.20155/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":"2026-07-05T11:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ylTWvb4Ks6uqBYx+WmvEG6Xm98re1W7QVcU5gXicIQWTMzLOAFPQ96YYCFLlZHcfaZkUMOMJj7mID0NB28ofCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:22:04.071969Z"},"content_sha256":"9ce2ad0c6daee0e2919943094647ef321b460b6c955500ca212823266d334219","schema_version":"1.0","event_id":"sha256:9ce2ad0c6daee0e2919943094647ef321b460b6c955500ca212823266d334219"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBWBH3ZDC6WHZLTBHTPB462CFV/bundle.json","state_url":"https://pith.science/pith/XBWBH3ZDC6WHZLTBHTPB462CFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBWBH3ZDC6WHZLTBHTPB462CFV/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":"2026-07-06T12:22:04Z","links":{"resolver":"https://pith.science/pith/XBWBH3ZDC6WHZLTBHTPB462CFV","bundle":"https://pith.science/pith/XBWBH3ZDC6WHZLTBHTPB462CFV/bundle.json","state":"https://pith.science/pith/XBWBH3ZDC6WHZLTBHTPB462CFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBWBH3ZDC6WHZLTBHTPB462CFV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XBWBH3ZDC6WHZLTBHTPB462CFV","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":"2c0e9fc7e16abc6eb8cfb7b176cb729d81b0cca970da22d7a2e32ca2742250eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:57:08Z","title_canon_sha256":"e696905241e2b89550a90afddf411417a42be38578cd63612d4d8e0c93e35d7d"},"schema_version":"1.0","source":{"id":"2505.20155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20155","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20155v1","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20155","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"XBWBH3ZDC6WH","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"XBWBH3ZDC6WHZLTB","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"XBWBH3ZD","created_at":"2026-07-05T11:09:53Z"}],"graph_snapshots":[{"event_id":"sha256:9ce2ad0c6daee0e2919943094647ef321b460b6c955500ca212823266d334219","target":"graph","created_at":"2026-07-05T11:09:53Z","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/2505.20155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) deliver state-of-the-art capabilities across numerous tasks, but their immense size and inference costs pose significant computational challenges for practical deployment. While structured pruning offers a promising avenue for model compression, existing methods often struggle with the detrimental effects of aggressive, simultaneous width and depth reductions, leading to substantial performance degradation. This paper argues that a critical, often overlooked, aspect in making such aggressive joint pruning viable is the strategic re-initialization and adjustment of ","authors_text":"Can Chen, Fisher Yu, Hanting Chen, Huiling Zhen, Jialong Guo, Jiarui Qin, Jinpeng Li, Meng Zhang, Rongju Ruan, Ruiming Tang, Tao Yuan, Xiaojun Meng, Xinghao Chen, Yasheng Wang, Yehui Tang, Yichun Yin, Yunhe Wang (and Other Contributors), Zheyuan Bai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:57:08Z","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20155","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":"sha256:92cc3f4aa9afd7257e2e6c4206d8cc1862fca768df3a3f7301cd98cd0d78cae3","target":"record","created_at":"2026-07-05T11:09:53Z","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":"2c0e9fc7e16abc6eb8cfb7b176cb729d81b0cca970da22d7a2e32ca2742250eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:57:08Z","title_canon_sha256":"e696905241e2b89550a90afddf411417a42be38578cd63612d4d8e0c93e35d7d"},"schema_version":"1.0","source":{"id":"2505.20155","kind":"arxiv","version":1}},"canonical_sha256":"b86c13ef2317ac7cae613cde1e7b422d6417836e2790774271f3d373f9580f52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b86c13ef2317ac7cae613cde1e7b422d6417836e2790774271f3d373f9580f52","first_computed_at":"2026-07-05T11:09:53.436891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:53.436891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gdsiPuNfmUkEVSkbVJpwGBiZaL+sjwgMcOf7EO/vCdjE53Uonknqw6hBO7h0fNDXZMyA36tlsqBDniK+p10NCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:53.437482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92cc3f4aa9afd7257e2e6c4206d8cc1862fca768df3a3f7301cd98cd0d78cae3","sha256:9ce2ad0c6daee0e2919943094647ef321b460b6c955500ca212823266d334219"],"state_sha256":"9f80fe88e201c8b36d62896f1b931c655f16fcba6aa8b3cfb42aae4b4d75354d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vQaPOc9SiyrM5RKuo4vljz5iZEk+n/R/t4i6GfcJUH10K5fWuTRyTjeIxMX0oaUhU8A9GzFJlOw6jOaSuX29DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:22:04.074188Z","bundle_sha256":"b5a5a58291ec8b9c4f681f8ac2dc7c8b80112e001089dbe3c5d1afb03e96e81b"}}