{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4UTHW6YGM7TJSALZF2WNS7XPE3","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":"987461790903e0570221ee6b1d75d0c6e5e2e85a046833cfe75b39229b537708","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-10T17:59:21Z","title_canon_sha256":"03ae8f3de12465d1759bf16a776572f997c21d659daf58357589b0c44ccde13d"},"schema_version":"1.0","source":{"id":"2307.05591","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05591","created_at":"2026-07-05T10:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05591v4","created_at":"2026-07-05T10:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05591","created_at":"2026-07-05T10:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"4UTHW6YGM7TJ","created_at":"2026-07-05T10:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"4UTHW6YGM7TJSALZ","created_at":"2026-07-05T10:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"4UTHW6YG","created_at":"2026-07-05T10:11:13Z"}],"graph_snapshots":[{"event_id":"sha256:f34c52cd57d7cf06962c955aa490fc84a5c3d95afd120f15e5551cd17c00f0d4","target":"graph","created_at":"2026-07-05T10:11:13Z","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/2307.05591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, vision-language models like CLIP have advanced the state of the art in a variety of multi-modal tasks including image captioning and caption evaluation. Many approaches leverage CLIP for cross-modal retrieval to condition pre-trained language models on visual input. However, CLIP generally suffers from a mis-alignment of image and text modalities in the joint embedding space. We investigate efficient methods to linearly re-align the joint embedding space for the downstream task of image captioning. This leads to an efficient training protocol that merely requires computing a closed-f","authors_text":"Fabian Paischer, Markus Hofmarcher, Sepp Hochreiter, Thomas Adler","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-10T17:59:21Z","title":"Linear Alignment of Vision-language Models for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05591","kind":"arxiv","version":4},"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:d65ef7cba2e02f55a4af350f435b82cf7c8e03b459a6b9f642a1703573b3506d","target":"record","created_at":"2026-07-05T10:11:13Z","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":"987461790903e0570221ee6b1d75d0c6e5e2e85a046833cfe75b39229b537708","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-10T17:59:21Z","title_canon_sha256":"03ae8f3de12465d1759bf16a776572f997c21d659daf58357589b0c44ccde13d"},"schema_version":"1.0","source":{"id":"2307.05591","kind":"arxiv","version":4}},"canonical_sha256":"e5267b7b0667e69901792eacd97eef26ce788538717a8810acbb9077cf3011aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5267b7b0667e69901792eacd97eef26ce788538717a8810acbb9077cf3011aa","first_computed_at":"2026-07-05T10:11:13.356914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:13.356914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MsLi2RChQ59tRx2pRkmNTeC5bhj2lPefYMeGpaom3exrWfnGVNlOfEa5xKRRrGAPlSdr1i1y5HP/T0sYfMgMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:13.357454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.05591","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d65ef7cba2e02f55a4af350f435b82cf7c8e03b459a6b9f642a1703573b3506d","sha256:f34c52cd57d7cf06962c955aa490fc84a5c3d95afd120f15e5551cd17c00f0d4"],"state_sha256":"6c0df49485bf1fd5c56aa545a2c05fa3438c16fc6c7cba039776d0a725c38429"}