{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7IGMHAM7ZUGQV5R5ZDMBIYS2QA","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":"daadff5ced542e95c973f616539eddced1ae1accdb0822648d6088e399a1aa51","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T14:33:59Z","title_canon_sha256":"c597acd8ccd9c7e202d9738d7ad24bcbf4c8078f5579b53bd1b671a0c3ac1d73"},"schema_version":"1.0","source":{"id":"2504.06925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.06925","created_at":"2026-05-21T01:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2504.06925v1","created_at":"2026-05-21T01:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06925","created_at":"2026-05-21T01:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"7IGMHAM7ZUGQ","created_at":"2026-05-21T01:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"7IGMHAM7ZUGQV5R5","created_at":"2026-05-21T01:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"7IGMHAM7","created_at":"2026-05-21T01:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:ef30ac71c7ac7a1725ce5d67eb05c7b8e56bb288799ed382a5d16de97287307b","target":"graph","created_at":"2026-05-21T01:05:05Z","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/2504.06925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic dietary assessment based on food images remains a challenge, requiring precise food detection, segmentation, and classification. Vision-Language Models (VLMs) offer new possibilities by integrating visual and textual reasoning. In this study, we evaluate six state-of-the-art VLMs (ChatGPT, Gemini, Claude, Moondream, DeepSeek, and LLaVA), analyzing their capabilities in food recognition at different levels. For the experimental framework, we introduce the FoodNExTDB, a unique food image database that contains 9,263 expert-labeled images across 10 categories (e.g., \"protein source\"), 6","authors_text":"Aythami Morales, Blanca Lacruz-Pleguezuelos, Enrique Carrillo de Santa Pau, Guadalupe X.Baz\\'an, Isabel Espinosa-Salinas, Javier Ortega-Garcia, Julian Fierrez, Laura Judith Marcos Zambrano, Ruben Tolosana, Sergio Romero-Tapiador","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T14:33:59Z","title":"Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06925","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":"sha256:4bb5d86c1074751220ac6153c04813a9178ee0f1e5096cf40a7f6dae9bf11945","target":"record","created_at":"2026-05-21T01:05:05Z","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":"daadff5ced542e95c973f616539eddced1ae1accdb0822648d6088e399a1aa51","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T14:33:59Z","title_canon_sha256":"c597acd8ccd9c7e202d9738d7ad24bcbf4c8078f5579b53bd1b671a0c3ac1d73"},"schema_version":"1.0","source":{"id":"2504.06925","kind":"arxiv","version":1}},"canonical_sha256":"fa0cc3819fcd0d0af63dc8d814625a803d74a1c5cca8dd2fb6e08013894a621f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa0cc3819fcd0d0af63dc8d814625a803d74a1c5cca8dd2fb6e08013894a621f","first_computed_at":"2026-05-21T01:05:05.342060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:05.342060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FJspouZnoWu1jI5SY1vZrQZTePbuMc+En9HmIr/pPEVvI2zEa8NP0056QKfQPIG1VbfXtS6g0TOLeOJmu6g8CA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:05.343172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.06925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bb5d86c1074751220ac6153c04813a9178ee0f1e5096cf40a7f6dae9bf11945","sha256:ef30ac71c7ac7a1725ce5d67eb05c7b8e56bb288799ed382a5d16de97287307b"],"state_sha256":"91d141c5830560bcad30bac652178e713abb5f176076dbd4ef8cee17dd4829d3"}