{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IR4C7FJI4ICTBVS25OR5AO5Y6K","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":"4e3930fab551e7a1374801a54e85231a139cb45d698c3f3d6961c617bccdd460","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T11:56:22Z","title_canon_sha256":"9c19ec7c32114776c68811504b7352fdae45c15ca51a161362bd1a7591b01e6f"},"schema_version":"1.0","source":{"id":"2312.14991","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14991","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14991v2","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14991","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_12","alias_value":"IR4C7FJI4ICT","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_16","alias_value":"IR4C7FJI4ICTBVS2","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_8","alias_value":"IR4C7FJI","created_at":"2026-07-05T08:07:12Z"}],"graph_snapshots":[{"event_id":"sha256:4ac4cdce925ad02d92280e5aeab37c74a3e2e9f5df068f7dc1962a8a9ddc9d45","target":"graph","created_at":"2026-07-05T08:07:12Z","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/2312.14991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bin Zhu, Chong-Wah Ngo, Huiyan Qi, Jingjing Chen, Yuehao Yin, Yu-Gang Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T11:56:22Z","title":"FoodLMM: A Versatile Food Assistant using Large Multi-modal Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14991","kind":"arxiv","version":2},"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:e34061965e8ddc6795486ba5fbd7181a4fc28c973381a4bdc68d2b98daa07446","target":"record","created_at":"2026-07-05T08:07:12Z","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":"4e3930fab551e7a1374801a54e85231a139cb45d698c3f3d6961c617bccdd460","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T11:56:22Z","title_canon_sha256":"9c19ec7c32114776c68811504b7352fdae45c15ca51a161362bd1a7591b01e6f"},"schema_version":"1.0","source":{"id":"2312.14991","kind":"arxiv","version":2}},"canonical_sha256":"44782f9528e20530d65aeba3d03bb8f299d4d970e21037854afa5f6adf9b44e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44782f9528e20530d65aeba3d03bb8f299d4d970e21037854afa5f6adf9b44e7","first_computed_at":"2026-07-05T08:07:12.669219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:12.669219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rvXCUeQRlcgMSM8CkTTxgX+gm/C3bRUXuAajzkoXWmo4d3Ie9m9lMYpUVpBtTSThac9063vaVI99zEkT4jgtCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:12.669677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14991","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e34061965e8ddc6795486ba5fbd7181a4fc28c973381a4bdc68d2b98daa07446","sha256:4ac4cdce925ad02d92280e5aeab37c74a3e2e9f5df068f7dc1962a8a9ddc9d45"],"state_sha256":"96bb673a2c9ff69a4a288cb15c6b6bd0ab3a018e64c56544218aa1951ca02362"}