{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EMM5JBNWQNJEAPQYEVL4CWAKXW","short_pith_number":"pith:EMM5JBNW","schema_version":"1.0","canonical_sha256":"2319d485b68352403e182557c1580abd970a7c7a00145bd8644143b551f2478b","source":{"kind":"arxiv","id":"2206.06522","version":2},"attestation_state":"computed","paper":{"title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Jaemin Cho, Mohit Bansal, Yi-Lin Sung","submitted_at":"2022-06-13T23:51:56Z","abstract_excerpt":"Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of domains recently. However, it is costly to update the entire parameter set of large pre-trained models. Although recently proposed parameter-efficient transfer learning (PETL) techniques allow updating a small subset of parameters (e.g. only using 2% of parameters) inside a pre-trained backbone network for a new task, they only reduce the training memory requirement by up to 30%. This is because the gradient computation for the trainable parameters still requires backpropagation through the large pre-trai"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.06522","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-13T23:51:56Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"67f374c431e5a79f9b25feece29488ee3c25504a25ff85a5aa657d9bd9cee111","abstract_canon_sha256":"1f225bd041f627a2cfa8c7e814f75eb7fa9a737e3fad62c139269e9e416e3ad7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:02.726515Z","signature_b64":"jfFXCXSKgNh/5RBk7osGI/lG+nNW/j8m3NVeH01XtcY9hs1pVEfGvSBygeTDgo/L4CvRiyR0uwdSsDNBTyeVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2319d485b68352403e182557c1580abd970a7c7a00145bd8644143b551f2478b","last_reissued_at":"2026-07-05T05:12:02.726067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:02.726067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Jaemin Cho, Mohit Bansal, Yi-Lin Sung","submitted_at":"2022-06-13T23:51:56Z","abstract_excerpt":"Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of domains recently. However, it is costly to update the entire parameter set of large pre-trained models. Although recently proposed parameter-efficient transfer learning (PETL) techniques allow updating a small subset of parameters (e.g. only using 2% of parameters) inside a pre-trained backbone network for a new task, they only reduce the training memory requirement by up to 30%. This is because the gradient computation for the trainable parameters still requires backpropagation through the large pre-trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06522","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/2206.06522/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.06522","created_at":"2026-07-05T05:12:02.726117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06522v2","created_at":"2026-07-05T05:12:02.726117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06522","created_at":"2026-07-05T05:12:02.726117+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMM5JBNWQNJE","created_at":"2026-07-05T05:12:02.726117+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMM5JBNWQNJEAPQY","created_at":"2026-07-05T05:12:02.726117+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMM5JBNW","created_at":"2026-07-05T05:12:02.726117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2304.15010","citing_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW","json":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW.json","graph_json":"https://pith.science/api/pith-number/EMM5JBNWQNJEAPQYEVL4CWAKXW/graph.json","events_json":"https://pith.science/api/pith-number/EMM5JBNWQNJEAPQYEVL4CWAKXW/events.json","paper":"https://pith.science/paper/EMM5JBNW"},"agent_actions":{"view_html":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW","download_json":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW.json","view_paper":"https://pith.science/paper/EMM5JBNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06522&json=true","fetch_graph":"https://pith.science/api/pith-number/EMM5JBNWQNJEAPQYEVL4CWAKXW/graph.json","fetch_events":"https://pith.science/api/pith-number/EMM5JBNWQNJEAPQYEVL4CWAKXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW/action/storage_attestation","attest_author":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW/action/author_attestation","sign_citation":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW/action/citation_signature","submit_replication":"https://pith.science/pith/EMM5JBNWQNJEAPQYEVL4CWAKXW/action/replication_record"}},"created_at":"2026-07-05T05:12:02.726117+00:00","updated_at":"2026-07-05T05:12:02.726117+00:00"}