{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A2T33UVJJN37HO4OE442BHWTW3","short_pith_number":"pith:A2T33UVJ","canonical_record":{"source":{"id":"2205.11005","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-23T02:43:45Z","cross_cats_sorted":[],"title_canon_sha256":"61eedfd7b4601eb22a63f16e15ba0fe4c1819c0c28cc38f753e2b935443fc692","abstract_canon_sha256":"6298d1a496653deb1bf1736270ef50c5e901f4b107a4b35a7bd5c0a99eade429"},"schema_version":"1.0"},"canonical_sha256":"06a7bdd2a94b77f3bb8e2739a09ed3b6c87e8ff9eaa675d92f9227dfd7c58f2f","source":{"kind":"arxiv","id":"2205.11005","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11005","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11005v1","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11005","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"pith_short_12","alias_value":"A2T33UVJJN37","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"pith_short_16","alias_value":"A2T33UVJJN37HO4O","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"pith_short_8","alias_value":"A2T33UVJ","created_at":"2026-07-05T04:25:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A2T33UVJJN37HO4OE442BHWTW3","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11005","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-23T02:43:45Z","cross_cats_sorted":[],"title_canon_sha256":"61eedfd7b4601eb22a63f16e15ba0fe4c1819c0c28cc38f753e2b935443fc692","abstract_canon_sha256":"6298d1a496653deb1bf1736270ef50c5e901f4b107a4b35a7bd5c0a99eade429"},"schema_version":"1.0"},"canonical_sha256":"06a7bdd2a94b77f3bb8e2739a09ed3b6c87e8ff9eaa675d92f9227dfd7c58f2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:25.881421Z","signature_b64":"xDjCxhhLDKwoB0udb21Em3Atm770+VsDiNfiY48+rUSkgdlwCzYII8qVlYI98I6Gqw0AxQqeiVqTzdiuFNMUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06a7bdd2a94b77f3bb8e2739a09ed3b6c87e8ff9eaa675d92f9227dfd7c58f2f","last_reissued_at":"2026-07-05T04:25:25.881025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:25.881025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11005","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":"2026-07-05T04:25:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C9vEDXd6c4N81PUhAHnJ5QNMjNcRciz/8LadGEd5QAHFiwgrEHoRsFN3f/bVOn9ZYg7LGlV8c9XbxLViqlm/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:12:18.022400Z"},"content_sha256":"1e5e3f0817eba1230769362940cd38e19268cdb573c14d39691723704c1ec27f","schema_version":"1.0","event_id":"sha256:1e5e3f0817eba1230769362940cd38e19268cdb573c14d39691723704c1ec27f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A2T33UVJJN37HO4OE442BHWTW3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chuanqi Tan, Fuli Luo, Junjie Bai, Mengdi Wang, Shen Li, Songfang Huang, Yuchao Li","submitted_at":"2022-05-23T02:43:45Z","abstract_excerpt":"With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While most research focuses on how to accurately retain appropriate weights while maintaining the performance of the compressed model, there are challenges in the computational overhead and memory footprint of sparse training when compressing large-scale language models. To address this problem, we propose a Parameter-efficient Sparse Training (PST) method to reduce the number of trainable parameters during sparse-aware tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11005","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/2205.11005/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":"2026-07-05T04:25:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ydQM4oSyIf0qSrJBaLAN0el0qBn/95AGOiEyxCTjpcJLGy5QTHtD+qd8uM2VNsn+7RxnhnF3WDEIYIqmEueAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:12:18.023393Z"},"content_sha256":"2ae6fc6438898bf4fd5c0239ccb0fa3f9f9434b5ca8cfb9da9e27a4b94fae675","schema_version":"1.0","event_id":"sha256:2ae6fc6438898bf4fd5c0239ccb0fa3f9f9434b5ca8cfb9da9e27a4b94fae675"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2T33UVJJN37HO4OE442BHWTW3/bundle.json","state_url":"https://pith.science/pith/A2T33UVJJN37HO4OE442BHWTW3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2T33UVJJN37HO4OE442BHWTW3/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":"2026-08-18T04:12:18Z","links":{"resolver":"https://pith.science/pith/A2T33UVJJN37HO4OE442BHWTW3","bundle":"https://pith.science/pith/A2T33UVJJN37HO4OE442BHWTW3/bundle.json","state":"https://pith.science/pith/A2T33UVJJN37HO4OE442BHWTW3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2T33UVJJN37HO4OE442BHWTW3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A2T33UVJJN37HO4OE442BHWTW3","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":"6298d1a496653deb1bf1736270ef50c5e901f4b107a4b35a7bd5c0a99eade429","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-23T02:43:45Z","title_canon_sha256":"61eedfd7b4601eb22a63f16e15ba0fe4c1819c0c28cc38f753e2b935443fc692"},"schema_version":"1.0","source":{"id":"2205.11005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11005","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11005v1","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11005","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"pith_short_12","alias_value":"A2T33UVJJN37","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"pith_short_16","alias_value":"A2T33UVJJN37HO4O","created_at":"2026-07-05T04:25:25Z"},{"alias_kind":"pith_short_8","alias_value":"A2T33UVJ","created_at":"2026-07-05T04:25:25Z"}],"graph_snapshots":[{"event_id":"sha256:2ae6fc6438898bf4fd5c0239ccb0fa3f9f9434b5ca8cfb9da9e27a4b94fae675","target":"graph","created_at":"2026-07-05T04:25:25Z","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/2205.11005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While most research focuses on how to accurately retain appropriate weights while maintaining the performance of the compressed model, there are challenges in the computational overhead and memory footprint of sparse training when compressing large-scale language models. To address this problem, we propose a Parameter-efficient Sparse Training (PST) method to reduce the number of trainable parameters during sparse-aware tr","authors_text":"Chuanqi Tan, Fuli Luo, Junjie Bai, Mengdi Wang, Shen Li, Songfang Huang, Yuchao Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-23T02:43:45Z","title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11005","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":"sha256:1e5e3f0817eba1230769362940cd38e19268cdb573c14d39691723704c1ec27f","target":"record","created_at":"2026-07-05T04:25:25Z","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":"6298d1a496653deb1bf1736270ef50c5e901f4b107a4b35a7bd5c0a99eade429","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-23T02:43:45Z","title_canon_sha256":"61eedfd7b4601eb22a63f16e15ba0fe4c1819c0c28cc38f753e2b935443fc692"},"schema_version":"1.0","source":{"id":"2205.11005","kind":"arxiv","version":1}},"canonical_sha256":"06a7bdd2a94b77f3bb8e2739a09ed3b6c87e8ff9eaa675d92f9227dfd7c58f2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06a7bdd2a94b77f3bb8e2739a09ed3b6c87e8ff9eaa675d92f9227dfd7c58f2f","first_computed_at":"2026-07-05T04:25:25.881025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:25.881025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xDjCxhhLDKwoB0udb21Em3Atm770+VsDiNfiY48+rUSkgdlwCzYII8qVlYI98I6Gqw0AxQqeiVqTzdiuFNMUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:25.881421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e5e3f0817eba1230769362940cd38e19268cdb573c14d39691723704c1ec27f","sha256:2ae6fc6438898bf4fd5c0239ccb0fa3f9f9434b5ca8cfb9da9e27a4b94fae675"],"state_sha256":"d00d7676977d1535a6afce4d11653efb71c9a1935d43ba01c9b5f0542dca700e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j6QzH7+T2WQPpaET3dpgTKt25VjaQldpKNQEKMlTfGVSSGmpC1zPOtofJxjUkdHYQzlmp0PdZx5CGwsxHBw4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:12:18.028880Z","bundle_sha256":"f8af8927b4d3f3748b0a9ce34d3849c35eef6b09d052c389f5b8dde933a00c02"}}