{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IR4C7FJI4ICTBVS25OR5AO5Y6K","short_pith_number":"pith:IR4C7FJI","schema_version":"1.0","canonical_sha256":"44782f9528e20530d65aeba3d03bb8f299d4d970e21037854afa5f6adf9b44e7","source":{"kind":"arxiv","id":"2312.14991","version":2},"attestation_state":"computed","paper":{"title":"FoodLMM: A Versatile Food Assistant using Large Multi-modal Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Zhu, Chong-Wah Ngo, Huiyan Qi, Jingjing Chen, Yuehao Yin, Yu-Gang Jiang","submitted_at":"2023-12-22T11:56:22Z","abstract_excerpt":"Large Multi-modal Models (LMMs) have made impressive progress in many vision-language tasks. Nevertheless, the performance of general LMMs in specific domains is still far from satisfactory. This paper proposes FoodLMM, a versatile food assistant based on LMMs with various capabilities, including food recognition, ingredient recognition, recipe generation, nutrition estimation, food segmentation and multi-round conversation. To facilitate FoodLMM to deal with tasks beyond pure text output, we introduce a series of novel task-specific tokens and heads, enabling the model to predict food nutriti"},"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":"2312.14991","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T11:56:22Z","cross_cats_sorted":[],"title_canon_sha256":"9c19ec7c32114776c68811504b7352fdae45c15ca51a161362bd1a7591b01e6f","abstract_canon_sha256":"4e3930fab551e7a1374801a54e85231a139cb45d698c3f3d6961c617bccdd460"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:12.669677Z","signature_b64":"rvXCUeQRlcgMSM8CkTTxgX+gm/C3bRUXuAajzkoXWmo4d3Ie9m9lMYpUVpBtTSThac9063vaVI99zEkT4jgtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44782f9528e20530d65aeba3d03bb8f299d4d970e21037854afa5f6adf9b44e7","last_reissued_at":"2026-07-05T08:07:12.669219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:12.669219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoodLMM: A Versatile Food Assistant using Large Multi-modal Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Zhu, Chong-Wah Ngo, Huiyan Qi, Jingjing Chen, Yuehao Yin, Yu-Gang Jiang","submitted_at":"2023-12-22T11:56:22Z","abstract_excerpt":"Large Multi-modal Models (LMMs) have made impressive progress in many vision-language tasks. Nevertheless, the performance of general LMMs in specific domains is still far from satisfactory. This paper proposes FoodLMM, a versatile food assistant based on LMMs with various capabilities, including food recognition, ingredient recognition, recipe generation, nutrition estimation, food segmentation and multi-round conversation. To facilitate FoodLMM to deal with tasks beyond pure text output, we introduce a series of novel task-specific tokens and heads, enabling the model to predict food nutriti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14991","kind":"arxiv","version":2},"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/2312.14991/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":"2312.14991","created_at":"2026-07-05T08:07:12.669276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14991v2","created_at":"2026-07-05T08:07:12.669276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14991","created_at":"2026-07-05T08:07:12.669276+00:00"},{"alias_kind":"pith_short_12","alias_value":"IR4C7FJI4ICT","created_at":"2026-07-05T08:07:12.669276+00:00"},{"alias_kind":"pith_short_16","alias_value":"IR4C7FJI4ICTBVS2","created_at":"2026-07-05T08:07:12.669276+00:00"},{"alias_kind":"pith_short_8","alias_value":"IR4C7FJI","created_at":"2026-07-05T08:07:12.669276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.06925","citing_title":"Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K","json":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K.json","graph_json":"https://pith.science/api/pith-number/IR4C7FJI4ICTBVS25OR5AO5Y6K/graph.json","events_json":"https://pith.science/api/pith-number/IR4C7FJI4ICTBVS25OR5AO5Y6K/events.json","paper":"https://pith.science/paper/IR4C7FJI"},"agent_actions":{"view_html":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K","download_json":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K.json","view_paper":"https://pith.science/paper/IR4C7FJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14991&json=true","fetch_graph":"https://pith.science/api/pith-number/IR4C7FJI4ICTBVS25OR5AO5Y6K/graph.json","fetch_events":"https://pith.science/api/pith-number/IR4C7FJI4ICTBVS25OR5AO5Y6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K/action/storage_attestation","attest_author":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K/action/author_attestation","sign_citation":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K/action/citation_signature","submit_replication":"https://pith.science/pith/IR4C7FJI4ICTBVS25OR5AO5Y6K/action/replication_record"}},"created_at":"2026-07-05T08:07:12.669276+00:00","updated_at":"2026-07-05T08:07:12.669276+00:00"}