{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:POKKNFZQRDAEOQVKGQGXWC2DGZ","short_pith_number":"pith:POKKNFZQ","canonical_record":{"source":{"id":"2408.14721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T01:04:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e634ccf79cca4a5714b50a7f0c10c233783c0f133210f0c8ae1356562749775c","abstract_canon_sha256":"fd4c59f8bb8d59b391af102a357dca3061916cefce691f53b474e8dca4890c60"},"schema_version":"1.0"},"canonical_sha256":"7b94a6973088c04742aa340d7b0b433672f6b649d4c450e49158ea62cb96cb86","source":{"kind":"arxiv","id":"2408.14721","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14721","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14721v2","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14721","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"POKKNFZQRDAE","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"POKKNFZQRDAEOQVK","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"POKKNFZQ","created_at":"2026-07-05T10:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:POKKNFZQRDAEOQVKGQGXWC2DGZ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T01:04:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e634ccf79cca4a5714b50a7f0c10c233783c0f133210f0c8ae1356562749775c","abstract_canon_sha256":"fd4c59f8bb8d59b391af102a357dca3061916cefce691f53b474e8dca4890c60"},"schema_version":"1.0"},"canonical_sha256":"7b94a6973088c04742aa340d7b0b433672f6b649d4c450e49158ea62cb96cb86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:12.504156Z","signature_b64":"o1L5+A/AMxaDi6Aw3NrFFt18v1iW9uLQzcPdlurmKk2w/wOlQbv2VxAdOC32pppFCu8ACGKRS4VvfBib/fzJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b94a6973088c04742aa340d7b0b433672f6b649d4c450e49158ea62cb96cb86","last_reissued_at":"2026-07-05T10:05:12.503701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:12.503701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14721","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":"2026-07-05T10:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fpKsrr4rVwjXDDTCbbrp186/Q4BL4vcytk0rFpmAYX7wdOFOdvflP5su9HrQt+drdW79SJFFubgz6s8JsvTXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:38:22.735166Z"},"content_sha256":"890ec2d6d06d7879bbfa23e1ebd7187f69a73585c764553f0f12d2a23a2265e3","schema_version":"1.0","event_id":"sha256:890ec2d6d06d7879bbfa23e1ebd7187f69a73585c764553f0f12d2a23a2265e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:POKKNFZQRDAEOQVKGQGXWC2DGZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAT: Pruning-Aware Tuning for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Huanrui Yang, Li Du, Miao Wang, Rongyu Zhang, Yijiang Liu, Youxin Chen, Yuan Du","submitted_at":"2024-08-27T01:04:14Z","abstract_excerpt":"Large language models (LLMs) excel in language tasks, especially with supervised fine-tuning after pre-training. However, their substantial memory and computational requirements hinder practical applications. Structural pruning, which reduces less significant weight dimensions, is one solution. Yet, traditional post-hoc pruning often leads to significant performance loss, with limited recovery from further fine-tuning due to reduced capacity. Since the model fine-tuning refines the general and chaotic knowledge in pre-trained models, we aim to incorporate structural pruning with the fine-tunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14721","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/2408.14721/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":"2026-07-05T10:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dCil2PZovIYUoTKqXypdi5zzHHEJMqklZIG40UokDhozp746kla6L0iTO/Waktiufk7vJ0ZXqvgi88MEyJa0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:38:22.735686Z"},"content_sha256":"a811ef0acad7e6b394c9f2accfbab66370c937bc1cd44478184775cf4305b0c5","schema_version":"1.0","event_id":"sha256:a811ef0acad7e6b394c9f2accfbab66370c937bc1cd44478184775cf4305b0c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POKKNFZQRDAEOQVKGQGXWC2DGZ/bundle.json","state_url":"https://pith.science/pith/POKKNFZQRDAEOQVKGQGXWC2DGZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POKKNFZQRDAEOQVKGQGXWC2DGZ/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":"2026-07-07T02:38:22Z","links":{"resolver":"https://pith.science/pith/POKKNFZQRDAEOQVKGQGXWC2DGZ","bundle":"https://pith.science/pith/POKKNFZQRDAEOQVKGQGXWC2DGZ/bundle.json","state":"https://pith.science/pith/POKKNFZQRDAEOQVKGQGXWC2DGZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POKKNFZQRDAEOQVKGQGXWC2DGZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:POKKNFZQRDAEOQVKGQGXWC2DGZ","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":"fd4c59f8bb8d59b391af102a357dca3061916cefce691f53b474e8dca4890c60","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T01:04:14Z","title_canon_sha256":"e634ccf79cca4a5714b50a7f0c10c233783c0f133210f0c8ae1356562749775c"},"schema_version":"1.0","source":{"id":"2408.14721","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14721","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14721v2","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14721","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"POKKNFZQRDAE","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"POKKNFZQRDAEOQVK","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"POKKNFZQ","created_at":"2026-07-05T10:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:a811ef0acad7e6b394c9f2accfbab66370c937bc1cd44478184775cf4305b0c5","target":"graph","created_at":"2026-07-05T10:05:12Z","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/2408.14721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel in language tasks, especially with supervised fine-tuning after pre-training. However, their substantial memory and computational requirements hinder practical applications. Structural pruning, which reduces less significant weight dimensions, is one solution. Yet, traditional post-hoc pruning often leads to significant performance loss, with limited recovery from further fine-tuning due to reduced capacity. Since the model fine-tuning refines the general and chaotic knowledge in pre-trained models, we aim to incorporate structural pruning with the fine-tunin","authors_text":"Huanrui Yang, Li Du, Miao Wang, Rongyu Zhang, Yijiang Liu, Youxin Chen, Yuan Du","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T01:04:14Z","title":"PAT: Pruning-Aware Tuning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14721","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":"sha256:890ec2d6d06d7879bbfa23e1ebd7187f69a73585c764553f0f12d2a23a2265e3","target":"record","created_at":"2026-07-05T10:05:12Z","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":"fd4c59f8bb8d59b391af102a357dca3061916cefce691f53b474e8dca4890c60","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T01:04:14Z","title_canon_sha256":"e634ccf79cca4a5714b50a7f0c10c233783c0f133210f0c8ae1356562749775c"},"schema_version":"1.0","source":{"id":"2408.14721","kind":"arxiv","version":2}},"canonical_sha256":"7b94a6973088c04742aa340d7b0b433672f6b649d4c450e49158ea62cb96cb86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b94a6973088c04742aa340d7b0b433672f6b649d4c450e49158ea62cb96cb86","first_computed_at":"2026-07-05T10:05:12.503701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:12.503701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o1L5+A/AMxaDi6Aw3NrFFt18v1iW9uLQzcPdlurmKk2w/wOlQbv2VxAdOC32pppFCu8ACGKRS4VvfBib/fzJAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:12.504156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14721","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:890ec2d6d06d7879bbfa23e1ebd7187f69a73585c764553f0f12d2a23a2265e3","sha256:a811ef0acad7e6b394c9f2accfbab66370c937bc1cd44478184775cf4305b0c5"],"state_sha256":"afe1461f991e11a634ea367d272fe407c2f8c0cc70e0a0c50163001ba3d04534"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LnqSJuiv8qGLiNi9GNHcz6YjyvJuyFcetDwSiZIZTsxujZmPjbJ0GcD4iWpyS2A5TJDf35x26EC4w8gS/2OTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:38:22.738548Z","bundle_sha256":"9324be1056eb26bc2713fb0e14b6f2c56ec6dc096aac8ebf6987fe542f978359"}}