{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KX4CIXDCWR376JWVJXQPD5ZKGZ","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":"d2cfa791dfb7250b16bc451709fe3c0ac70a3eeea3ed75e8839cb6de9a48d065","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T10:04:19Z","title_canon_sha256":"132d665fcefbd44aab4885563b29491b8286f6476d557af984fec3f1a7262719"},"schema_version":"1.0","source":{"id":"2506.02708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02708","created_at":"2026-07-05T11:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02708v1","created_at":"2026-07-05T11:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02708","created_at":"2026-07-05T11:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"KX4CIXDCWR37","created_at":"2026-07-05T11:15:06Z"},{"alias_kind":"pith_short_16","alias_value":"KX4CIXDCWR376JWV","created_at":"2026-07-05T11:15:06Z"},{"alias_kind":"pith_short_8","alias_value":"KX4CIXDC","created_at":"2026-07-05T11:15:06Z"}],"graph_snapshots":[{"event_id":"sha256:efed673089c955000297716066545f9f44873f4ed754a7c091dc979f155e10f7","target":"graph","created_at":"2026-07-05T11:15:06Z","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/2506.02708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image scoring is a crucial task in numerous real-world applications. To trust a model's judgment, understanding its rationale is essential. This paper proposes a novel training method for Vision Language Models (VLMs) to generate not only image scores but also corresponding justifications in natural language. Leveraging only an image scoring dataset and an instruction-tuned VLM, our method enables self-training, utilizing the VLM's generated text without relying on external data or models. In addition, we introduce a simple method for creating a dataset designed to improve alignment between pr","authors_text":"Naoto Tanji, Toshihiko Yamasaki","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T10:04:19Z","title":"Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02708","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:ded967d2e9edaed5e4008e614c90c4c037e1dfb8fdbfae08ec9c62f8798fb788","target":"record","created_at":"2026-07-05T11:15:06Z","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":"d2cfa791dfb7250b16bc451709fe3c0ac70a3eeea3ed75e8839cb6de9a48d065","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T10:04:19Z","title_canon_sha256":"132d665fcefbd44aab4885563b29491b8286f6476d557af984fec3f1a7262719"},"schema_version":"1.0","source":{"id":"2506.02708","kind":"arxiv","version":1}},"canonical_sha256":"55f8245c62b477ff26d54de0f1f72a367f417765bacbd0974f79157e31bb4c78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55f8245c62b477ff26d54de0f1f72a367f417765bacbd0974f79157e31bb4c78","first_computed_at":"2026-07-05T11:15:06.886010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:06.886010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nCI8RDuvOdpI3b2hB7UxkcDj7FnPxL5Uk4hs9FVfQ0BSLFSVLXP8W19/DUF+uih+RXm8EphBw16ShHLjGHeAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:06.886568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ded967d2e9edaed5e4008e614c90c4c037e1dfb8fdbfae08ec9c62f8798fb788","sha256:efed673089c955000297716066545f9f44873f4ed754a7c091dc979f155e10f7"],"state_sha256":"987424274bc9c25ee73352ebb22c92332df0c105cd55a86b3b9c37908d5ca191"}