{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GQS2SZUNMYWYEAF43JWD546D3J","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":"f4564a174ede6b584a2d45281867720967f4401603a3abac5e283981c578ed10","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T00:43:50Z","title_canon_sha256":"b85f963725e23f6b3f1da833386dd052b967c69188fb6ebd40a75ea7392c47f6"},"schema_version":"1.0","source":{"id":"2501.18824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18824","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18824v1","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18824","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_12","alias_value":"GQS2SZUNMYWY","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_16","alias_value":"GQS2SZUNMYWYEAF4","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_8","alias_value":"GQS2SZUN","created_at":"2026-07-05T10:07:52Z"}],"graph_snapshots":[{"event_id":"sha256:70a68d6bd3bd7bf6a9902bad7cfe39fefdc716efc7dccb36e63f6c2c3216ab5b","target":"graph","created_at":"2026-07-05T10:07:52Z","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/2501.18824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing methods may reduce certain parts of the memory required for fine-tuning, they still require caching all intermediate activations computed in the forward pass to update weights during the backward pass. In this work, we develop TokenTune, a method to reduce memory usage, specifically the memory to store intermediate activations, in the fine-tuning of transformer-b","authors_text":"Antoine Simoulin, Grey Yang, Namyong Park, Xiaoyi Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T00:43:50Z","title":"Memory-Efficient Fine-Tuning of Transformers via Token Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18824","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:cf889c73ed4341b9361add9b613b9c957f4c234daad261c4c9eb2d6d696e4a23","target":"record","created_at":"2026-07-05T10:07:52Z","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":"f4564a174ede6b584a2d45281867720967f4401603a3abac5e283981c578ed10","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T00:43:50Z","title_canon_sha256":"b85f963725e23f6b3f1da833386dd052b967c69188fb6ebd40a75ea7392c47f6"},"schema_version":"1.0","source":{"id":"2501.18824","kind":"arxiv","version":1}},"canonical_sha256":"3425a9668d662d8200bcda6c3ef3c3da54b849f13a9448b5b8075cf482bbe191","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3425a9668d662d8200bcda6c3ef3c3da54b849f13a9448b5b8075cf482bbe191","first_computed_at":"2026-07-05T10:07:52.169863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:52.169863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OrWNEfjcPPQBF6x2dusgS3I6r7zmQzTXV/re/IrianMAomieWB5afNE0NdaAphSDQ41uRxFG3qwAAaZBXdXVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:52.170364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf889c73ed4341b9361add9b613b9c957f4c234daad261c4c9eb2d6d696e4a23","sha256:70a68d6bd3bd7bf6a9902bad7cfe39fefdc716efc7dccb36e63f6c2c3216ab5b"],"state_sha256":"04bf9c97e1f2ad564f1c0d198946c3410cec279d13c01ef1174f766491730ca3"}