{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SRMIO5AZC3QLSJQGGIRFUOGPP5","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":"a9c26624c4e2ee92ccaa1d2c5e110bf4ae7af1f4c9a27c4314d0df1922e1733c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T12:57:22Z","title_canon_sha256":"d3234c27ff5d7ba6d667c25ccc35f131e64549693a8516f6016ed6733b953f6e"},"schema_version":"1.0","source":{"id":"2404.01911","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01911","created_at":"2026-07-05T08:03:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01911v1","created_at":"2026-07-05T08:03:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01911","created_at":"2026-07-05T08:03:33Z"},{"alias_kind":"pith_short_12","alias_value":"SRMIO5AZC3QL","created_at":"2026-07-05T08:03:33Z"},{"alias_kind":"pith_short_16","alias_value":"SRMIO5AZC3QLSJQG","created_at":"2026-07-05T08:03:33Z"},{"alias_kind":"pith_short_8","alias_value":"SRMIO5AZ","created_at":"2026-07-05T08:03:33Z"}],"graph_snapshots":[{"event_id":"sha256:5df8c0f49e778689ab50a36e4c67bdf6c83bdf4d8710c2597abe160e7237e592","target":"graph","created_at":"2026-07-05T08:03:33Z","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/2404.01911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present an unsupervised method for enhancing an image captioning model (in our case, BLIP2) using reinforcement learning and vision-language models like CLIP and BLIP2-ITM as reward models. The RL-tuned model is able to generate longer and more comprehensive descriptions. Our model reaches impressive 0.90 R@1 CLIP Recall score on MS-COCO Carpathy Test Split.\n  Weights are available at https://huggingface.co/sashakunitsyn/vlrm-blip2-opt-2.7b.","authors_text":"Alexander Kunitsyn, Andrei Ivaniuta, Maksim Dzabraev","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T12:57:22Z","title":"VLRM: Vision-Language Models act as Reward Models for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01911","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":"sha256:4a132b424030b666b6e081a763912d6fafe432b5d56c3d4dd4927e5e9a144f82","target":"record","created_at":"2026-07-05T08:03:33Z","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":"a9c26624c4e2ee92ccaa1d2c5e110bf4ae7af1f4c9a27c4314d0df1922e1733c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T12:57:22Z","title_canon_sha256":"d3234c27ff5d7ba6d667c25ccc35f131e64549693a8516f6016ed6733b953f6e"},"schema_version":"1.0","source":{"id":"2404.01911","kind":"arxiv","version":1}},"canonical_sha256":"945887741916e0b9260632225a38cf7f5b0e14822dcbd53a9383c52892228fed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"945887741916e0b9260632225a38cf7f5b0e14822dcbd53a9383c52892228fed","first_computed_at":"2026-07-05T08:03:33.420461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:33.420461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XLvDb+6UpZjr2LHAx7gxaD+CsCfFjN0lPgpM2tRvDmZn5P9WrJtClkw3Yy8ZwavCqO+MGjgXhXhRv8YpJqBICw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:33.420843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01911","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a132b424030b666b6e081a763912d6fafe432b5d56c3d4dd4927e5e9a144f82","sha256:5df8c0f49e778689ab50a36e4c67bdf6c83bdf4d8710c2597abe160e7237e592"],"state_sha256":"a672a618297eea86f15fd74672004d69148a8230d5744396083880c752e5412d"}