{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XWXWUSIK452TX5VHJIHCDYSSCX","short_pith_number":"pith:XWXWUSIK","schema_version":"1.0","canonical_sha256":"bdaf6a490ae7753bf6a74a0e21e25215df68a94e0dc895a0522afa6a3b591e08","source":{"kind":"arxiv","id":"2308.14391","version":2},"attestation_state":"computed","paper":{"title":"FIRE: Food Image to REcipe generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dhiraj Chaurasia, Filip Ilievski, Omkar Masur, Prateek Chhikara, Yifan Jiang","submitted_at":"2023-08-28T08:14:20Z","abstract_excerpt":"Food computing has emerged as a prominent multidisciplinary field of research in recent years. An ambitious goal of food computing is to develop end-to-end intelligent systems capable of autonomously producing recipe information for a food image. Current image-to-recipe methods are retrieval-based and their success depends heavily on the dataset size and diversity, as well as the quality of learned embeddings. Meanwhile, the emergence of powerful attention-based vision and language models presents a promising avenue for accurate and generalizable recipe generation, which has yet to be extensiv"},"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":"2308.14391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T08:14:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8d3c09d62f481ad1db3f09e81a4c8d9b2eafc37f60c6d6ff02922144e2716d93","abstract_canon_sha256":"29dee6ba9d94e0278d6cd548173666eb00628199ccc649e5996441f078bf8dab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:59.147093Z","signature_b64":"X94bkqSpmmnWWZhivCYQ3tRAoojmk7z/oUVCKQzJbVixtYpcbv6RArU6SL4HedvvXnFO4EQcAFETrthjpkpBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdaf6a490ae7753bf6a74a0e21e25215df68a94e0dc895a0522afa6a3b591e08","last_reissued_at":"2026-07-05T08:17:59.146618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:59.146618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FIRE: Food Image to REcipe generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dhiraj Chaurasia, Filip Ilievski, Omkar Masur, Prateek Chhikara, Yifan Jiang","submitted_at":"2023-08-28T08:14:20Z","abstract_excerpt":"Food computing has emerged as a prominent multidisciplinary field of research in recent years. An ambitious goal of food computing is to develop end-to-end intelligent systems capable of autonomously producing recipe information for a food image. Current image-to-recipe methods are retrieval-based and their success depends heavily on the dataset size and diversity, as well as the quality of learned embeddings. Meanwhile, the emergence of powerful attention-based vision and language models presents a promising avenue for accurate and generalizable recipe generation, which has yet to be extensiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14391","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/2308.14391/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":"2308.14391","created_at":"2026-07-05T08:17:59.146682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14391v2","created_at":"2026-07-05T08:17:59.146682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14391","created_at":"2026-07-05T08:17:59.146682+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWXWUSIK452T","created_at":"2026-07-05T08:17:59.146682+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWXWUSIK452TX5VH","created_at":"2026-07-05T08:17:59.146682+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWXWUSIK","created_at":"2026-07-05T08:17:59.146682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04986","citing_title":"Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX","json":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX.json","graph_json":"https://pith.science/api/pith-number/XWXWUSIK452TX5VHJIHCDYSSCX/graph.json","events_json":"https://pith.science/api/pith-number/XWXWUSIK452TX5VHJIHCDYSSCX/events.json","paper":"https://pith.science/paper/XWXWUSIK"},"agent_actions":{"view_html":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX","download_json":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX.json","view_paper":"https://pith.science/paper/XWXWUSIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14391&json=true","fetch_graph":"https://pith.science/api/pith-number/XWXWUSIK452TX5VHJIHCDYSSCX/graph.json","fetch_events":"https://pith.science/api/pith-number/XWXWUSIK452TX5VHJIHCDYSSCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX/action/storage_attestation","attest_author":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX/action/author_attestation","sign_citation":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX/action/citation_signature","submit_replication":"https://pith.science/pith/XWXWUSIK452TX5VHJIHCDYSSCX/action/replication_record"}},"created_at":"2026-07-05T08:17:59.146682+00:00","updated_at":"2026-07-05T08:17:59.146682+00:00"}