{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:537RCFLTRUOWGR43TUHMMMBGMT","short_pith_number":"pith:537RCFLT","canonical_record":{"source":{"id":"2312.10365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-12-16T07:44:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d513bf66af7f4ab4ca3e8ea23ebd9624aa0862300bdb04c6ac098b6fca11956e","abstract_canon_sha256":"007160deae52ed64f9b8adc76d5ff475762cc5d6164e80533c2a823fd76e70c5"},"schema_version":"1.0"},"canonical_sha256":"eeff1115738d1d63479b9d0ec6302664db9e47a946f5fbe4813ea5be50c0355a","source":{"kind":"arxiv","id":"2312.10365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10365","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10365v1","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10365","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"pith_short_12","alias_value":"537RCFLTRUOW","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"pith_short_16","alias_value":"537RCFLTRUOWGR43","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"pith_short_8","alias_value":"537RCFLT","created_at":"2026-07-05T07:25:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:537RCFLTRUOWGR43TUHMMMBGMT","target":"record","payload":{"canonical_record":{"source":{"id":"2312.10365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-12-16T07:44:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d513bf66af7f4ab4ca3e8ea23ebd9624aa0862300bdb04c6ac098b6fca11956e","abstract_canon_sha256":"007160deae52ed64f9b8adc76d5ff475762cc5d6164e80533c2a823fd76e70c5"},"schema_version":"1.0"},"canonical_sha256":"eeff1115738d1d63479b9d0ec6302664db9e47a946f5fbe4813ea5be50c0355a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:05.561137Z","signature_b64":"SEm4Y4hzODGE7Z+ThTl/FANP4oI7DE9paQr9E/fF5nRpjiS/8Pkw+2NbDBDDBvBdK3sMdlgOCm9bbT2OHZAtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeff1115738d1d63479b9d0ec6302664db9e47a946f5fbe4813ea5be50c0355a","last_reissued_at":"2026-07-05T07:25:05.560751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:05.560751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.10365","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":"2026-07-05T07:25:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FfaXV3u9prQlk42D5CP8IybOQt0Ew9d/vW9LIclR7LkXiAWg+iEYgci2FGGBffuRK8G+/eP4zDiIS5Qn+8xjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:40:10.094983Z"},"content_sha256":"23b053a9f3e7e8385a1ac81cf9b144f014a03043bdd235840a574df3f2f612ed","schema_version":"1.0","event_id":"sha256:23b053a9f3e7e8385a1ac81cf9b144f014a03043bdd235840a574df3f2f612ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:537RCFLTRUOWGR43TUHMMMBGMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPT: Fine-Tuning Transformer-based Language Models Efficiently with Sparsification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Han Yang, James Cheng, Peiqi Yin, Xiao Yan, Yuntao Gui","submitted_at":"2023-12-16T07:44:52Z","abstract_excerpt":"Transformer-based large language models (e.g., BERT and GPT) achieve great success, and fine-tuning, which tunes a pre-trained model on a task-specific dataset, is the standard practice to utilize these models for downstream tasks. However, Transformer fine-tuning has long running time and high memory consumption due to the large size of the models. We propose the SPT system to fine-tune Transformer-based models efficiently by introducing sparsity. We observe that the memory consumption of Transformer mainly comes from storing attention weights for multi-head attention (MHA), and the majority "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10365","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/2312.10365/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":"2026-07-05T07:25:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EAYwXs6Lg5S04wPPJtTm//WQddYV8jHTuwO0xJweMA/OOgB3yRBjC4y+TQAKlnfm+uFfuyEkPFCaMi75+HD8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:40:10.096010Z"},"content_sha256":"7b3d8ebf8d745f8fde207f63fb60da536ff9993f1f4249eb4e9aa7c87fb304ef","schema_version":"1.0","event_id":"sha256:7b3d8ebf8d745f8fde207f63fb60da536ff9993f1f4249eb4e9aa7c87fb304ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/537RCFLTRUOWGR43TUHMMMBGMT/bundle.json","state_url":"https://pith.science/pith/537RCFLTRUOWGR43TUHMMMBGMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/537RCFLTRUOWGR43TUHMMMBGMT/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":"2026-07-06T08:40:10Z","links":{"resolver":"https://pith.science/pith/537RCFLTRUOWGR43TUHMMMBGMT","bundle":"https://pith.science/pith/537RCFLTRUOWGR43TUHMMMBGMT/bundle.json","state":"https://pith.science/pith/537RCFLTRUOWGR43TUHMMMBGMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/537RCFLTRUOWGR43TUHMMMBGMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:537RCFLTRUOWGR43TUHMMMBGMT","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":"007160deae52ed64f9b8adc76d5ff475762cc5d6164e80533c2a823fd76e70c5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-12-16T07:44:52Z","title_canon_sha256":"d513bf66af7f4ab4ca3e8ea23ebd9624aa0862300bdb04c6ac098b6fca11956e"},"schema_version":"1.0","source":{"id":"2312.10365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10365","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10365v1","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10365","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"pith_short_12","alias_value":"537RCFLTRUOW","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"pith_short_16","alias_value":"537RCFLTRUOWGR43","created_at":"2026-07-05T07:25:05Z"},{"alias_kind":"pith_short_8","alias_value":"537RCFLT","created_at":"2026-07-05T07:25:05Z"}],"graph_snapshots":[{"event_id":"sha256:7b3d8ebf8d745f8fde207f63fb60da536ff9993f1f4249eb4e9aa7c87fb304ef","target":"graph","created_at":"2026-07-05T07:25:05Z","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/2312.10365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based large language models (e.g., BERT and GPT) achieve great success, and fine-tuning, which tunes a pre-trained model on a task-specific dataset, is the standard practice to utilize these models for downstream tasks. However, Transformer fine-tuning has long running time and high memory consumption due to the large size of the models. We propose the SPT system to fine-tune Transformer-based models efficiently by introducing sparsity. We observe that the memory consumption of Transformer mainly comes from storing attention weights for multi-head attention (MHA), and the majority ","authors_text":"Han Yang, James Cheng, Peiqi Yin, Xiao Yan, Yuntao Gui","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-12-16T07:44:52Z","title":"SPT: Fine-Tuning Transformer-based Language Models Efficiently with Sparsification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10365","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":"sha256:23b053a9f3e7e8385a1ac81cf9b144f014a03043bdd235840a574df3f2f612ed","target":"record","created_at":"2026-07-05T07:25:05Z","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":"007160deae52ed64f9b8adc76d5ff475762cc5d6164e80533c2a823fd76e70c5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-12-16T07:44:52Z","title_canon_sha256":"d513bf66af7f4ab4ca3e8ea23ebd9624aa0862300bdb04c6ac098b6fca11956e"},"schema_version":"1.0","source":{"id":"2312.10365","kind":"arxiv","version":1}},"canonical_sha256":"eeff1115738d1d63479b9d0ec6302664db9e47a946f5fbe4813ea5be50c0355a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eeff1115738d1d63479b9d0ec6302664db9e47a946f5fbe4813ea5be50c0355a","first_computed_at":"2026-07-05T07:25:05.560751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:05.560751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SEm4Y4hzODGE7Z+ThTl/FANP4oI7DE9paQr9E/fF5nRpjiS/8Pkw+2NbDBDDBvBdK3sMdlgOCm9bbT2OHZAtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:05.561137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23b053a9f3e7e8385a1ac81cf9b144f014a03043bdd235840a574df3f2f612ed","sha256:7b3d8ebf8d745f8fde207f63fb60da536ff9993f1f4249eb4e9aa7c87fb304ef"],"state_sha256":"17aa341492a88d7e269f882f9e075779c011108b7373aef3ba8f05478011a730"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mkPRZjMfjp3PL48EHkQBsJ218xDL26bNi5IwQCubJW9N1ZrzHnb5wtrP/W3zyQK5MEjxHGU29vgmb9XvekqwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:40:10.098409Z","bundle_sha256":"aefea3c3cbc93b033149a8655467b5894ee82395adc9fff806d5fcd300deff0c"}}