{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X2QZUK4F2MFA7DRSNUZWIZ45XJ","short_pith_number":"pith:X2QZUK4F","schema_version":"1.0","canonical_sha256":"bea19a2b85d30a0f8e326d3364679dba4064bf6f85e3da40814e6eedfcb4962f","source":{"kind":"arxiv","id":"2606.04986","version":1},"attestation_state":"computed","paper":{"title":"Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Haoyi Jiang, Wei Yang, Wenjie Zhu, Wenyu Liu, Xinggang Wang, Yongkang Li, Yu Zhu","submitted_at":"2026-06-03T15:07:12Z","abstract_excerpt":"Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (SFT), which often limits reasoning and generalization capabilities. Moreover, high-quality large-scale nutritional annotations remain scarce. To address these issues, we introduce CalorieBench-80K, a large-scale benchmark with curated calorie labels and dietary advice annotations. To the best of our knowledge, it is the first food image benchmark to incorporate Chain-of-Thought (CoT) annotations for calorie reasoning. We also propose Food-R1, a "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.04986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T15:07:12Z","cross_cats_sorted":[],"title_canon_sha256":"52490c2c0b5282ec8b0277b9eb6e331491559f2595c0f773892d1ffa700c3955","abstract_canon_sha256":"3fc697bec2729c97e8f8a4c6d5afa4f8fd61ba4c19395cb86ee500c00ffccbe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:59.774753Z","signature_b64":"cZvJSQ7lvz0Iw/mOx8A54JH4PvFVoLD9mLQ3y8oiTwpeb8uL6WFkSlZFj1hGfQvT5ySidKVWPPPFtPespAfEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bea19a2b85d30a0f8e326d3364679dba4064bf6f85e3da40814e6eedfcb4962f","last_reissued_at":"2026-06-04T01:09:59.773271Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:59.773271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Haoyi Jiang, Wei Yang, Wenjie Zhu, Wenyu Liu, Xinggang Wang, Yongkang Li, Yu Zhu","submitted_at":"2026-06-03T15:07:12Z","abstract_excerpt":"Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (SFT), which often limits reasoning and generalization capabilities. Moreover, high-quality large-scale nutritional annotations remain scarce. To address these issues, we introduce CalorieBench-80K, a large-scale benchmark with curated calorie labels and dietary advice annotations. To the best of our knowledge, it is the first food image benchmark to incorporate Chain-of-Thought (CoT) annotations for calorie reasoning. We also propose Food-R1, a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04986","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.04986/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.04986","created_at":"2026-06-04T01:09:59.773881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04986v1","created_at":"2026-06-04T01:09:59.773881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04986","created_at":"2026-06-04T01:09:59.773881+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2QZUK4F2MFA","created_at":"2026-06-04T01:09:59.773881+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2QZUK4F2MFA7DRS","created_at":"2026-06-04T01:09:59.773881+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2QZUK4F","created_at":"2026-06-04T01:09:59.773881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ","json":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ.json","graph_json":"https://pith.science/api/pith-number/X2QZUK4F2MFA7DRSNUZWIZ45XJ/graph.json","events_json":"https://pith.science/api/pith-number/X2QZUK4F2MFA7DRSNUZWIZ45XJ/events.json","paper":"https://pith.science/paper/X2QZUK4F"},"agent_actions":{"view_html":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ","download_json":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ.json","view_paper":"https://pith.science/paper/X2QZUK4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04986&json=true","fetch_graph":"https://pith.science/api/pith-number/X2QZUK4F2MFA7DRSNUZWIZ45XJ/graph.json","fetch_events":"https://pith.science/api/pith-number/X2QZUK4F2MFA7DRSNUZWIZ45XJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ/action/storage_attestation","attest_author":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ/action/author_attestation","sign_citation":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ/action/citation_signature","submit_replication":"https://pith.science/pith/X2QZUK4F2MFA7DRSNUZWIZ45XJ/action/replication_record"}},"created_at":"2026-06-04T01:09:59.773881+00:00","updated_at":"2026-06-04T01:09:59.773881+00:00"}