{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QYVCKSH77GLKUE6CH7AJSH6XR4","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":"241d8bc3edc74aaf7acdb02fc42d3e40805f7d6ccd50378df7e753418460e5e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-11T16:32:28Z","title_canon_sha256":"618abb72ff61df02a84417cd316af5cfe4e69c47cc5f89425f8fc470cd406075"},"schema_version":"1.0","source":{"id":"2302.05738","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05738","created_at":"2026-07-05T05:52:26Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05738v2","created_at":"2026-07-05T05:52:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05738","created_at":"2026-07-05T05:52:26Z"},{"alias_kind":"pith_short_12","alias_value":"QYVCKSH77GLK","created_at":"2026-07-05T05:52:26Z"},{"alias_kind":"pith_short_16","alias_value":"QYVCKSH77GLKUE6C","created_at":"2026-07-05T05:52:26Z"},{"alias_kind":"pith_short_8","alias_value":"QYVCKSH7","created_at":"2026-07-05T05:52:26Z"}],"graph_snapshots":[{"event_id":"sha256:c3c056009d8bcb04fa384d3414a7f4615af725d6580b8e177d17be6f1d66b248","target":"graph","created_at":"2026-07-05T05:52:26Z","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/2302.05738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP. However, similar gains have not been observed in many other modalities due to a lack of relevant pretrained models. In this work, we propose ORCA, a general cross-modal fine-tuning framework that extends the applicability of a single large-scale pretrained model to diverse modalities. ORCA adapts to a target task via an align-then-refine workflow: given the target input, ORCA first learns an embedding network that aligns the embedded feature distribution with the pretrain","authors_text":"Ameet Talwalkar, Corey Staten, Graham Neubig, Junhong Shen, Liam Li, Lucio M. Dery, Mikhail Khodak","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-11T16:32:28Z","title":"Cross-Modal Fine-Tuning: Align then Refine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05738","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:e2536f07c02df0dca6b1e530430d3918a8dc0ca26e3dba55a5cd936a8e3ab827","target":"record","created_at":"2026-07-05T05:52:26Z","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":"241d8bc3edc74aaf7acdb02fc42d3e40805f7d6ccd50378df7e753418460e5e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-11T16:32:28Z","title_canon_sha256":"618abb72ff61df02a84417cd316af5cfe4e69c47cc5f89425f8fc470cd406075"},"schema_version":"1.0","source":{"id":"2302.05738","kind":"arxiv","version":2}},"canonical_sha256":"862a2548fff996aa13c23fc0991fd78f265ef99ab58630d9eee6af17a9c875e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"862a2548fff996aa13c23fc0991fd78f265ef99ab58630d9eee6af17a9c875e2","first_computed_at":"2026-07-05T05:52:26.012156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:26.012156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iQ4Ryo95NcyOdrI1C28mrIgMD4Ofj/BAMhJKic7X8XdaDHufavTp4J85t+7+9egSZ/ysy/CCInIwRvva+z8/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:26.012608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05738","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2536f07c02df0dca6b1e530430d3918a8dc0ca26e3dba55a5cd936a8e3ab827","sha256:c3c056009d8bcb04fa384d3414a7f4615af725d6580b8e177d17be6f1d66b248"],"state_sha256":"8628e8fe000dc2f022aaec7e087cbcb274e3c7580c5830367742b3aa9b04a751"}