{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NTSCKTPT2KFFJXGTG56UIQYLDK","short_pith_number":"pith:NTSCKTPT","schema_version":"1.0","canonical_sha256":"6ce4254df3d28a54dcd3377d44430b1aa2c3667a77c844456ba2cb1ff9e3d89e","source":{"kind":"arxiv","id":"2607.25794","version":1},"attestation_state":"computed","paper":{"title":"Fine-Grained Food Image Understanding via Target-Aware Data Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bruce Coburn, Fengqing Zhu, Jinge Ma, Jui-Feng Chi, Wei-Lun Chu","submitted_at":"2026-07-28T14:44:56Z","abstract_excerpt":"Fine-grained food visual--semantic understanding requires models to capture subtle distinctions across ingredients, cooking methods, doneness, color, texture, and plate composition. Although CLIP-style vision-language models provide a natural framework for this task, their effectiveness is limited when training relies on heterogeneous web-collected image--text pairs. Such data often exhibit a web-to-target domain gap and cross-modal misalignment, where images differ from the target distribution and captions are noisy, multilingual, or weakly grounded in visual content. We propose a data-centri"},"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":"2607.25794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T14:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"438027aae97c28233daa4cf08ca66ad33ce748e3b881a4b7f185658e50bf7b7b","abstract_canon_sha256":"81e3222971b4809154bbb88c626c6d5f0c74469e6e902251b04c256c280f5da2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:26:03.047542Z","signature_b64":"eYGjCu6Vsw32Rw6Dc0nxdENpQIY636fEK6INadHPOBdGiIiEJlcPEcJQADV3FB/3Vy/TYRSRSKekMv8wKRJfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ce4254df3d28a54dcd3377d44430b1aa2c3667a77c844456ba2cb1ff9e3d89e","last_reissued_at":"2026-07-29T01:26:03.046603Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:26:03.046603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Food Image Understanding via Target-Aware Data Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bruce Coburn, Fengqing Zhu, Jinge Ma, Jui-Feng Chi, Wei-Lun Chu","submitted_at":"2026-07-28T14:44:56Z","abstract_excerpt":"Fine-grained food visual--semantic understanding requires models to capture subtle distinctions across ingredients, cooking methods, doneness, color, texture, and plate composition. Although CLIP-style vision-language models provide a natural framework for this task, their effectiveness is limited when training relies on heterogeneous web-collected image--text pairs. Such data often exhibit a web-to-target domain gap and cross-modal misalignment, where images differ from the target distribution and captions are noisy, multilingual, or weakly grounded in visual content. We propose a data-centri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25794","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/2607.25794/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":"2607.25794","created_at":"2026-07-29T01:26:03.047077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25794v1","created_at":"2026-07-29T01:26:03.047077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25794","created_at":"2026-07-29T01:26:03.047077+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTSCKTPT2KFF","created_at":"2026-07-29T01:26:03.047077+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTSCKTPT2KFFJXGT","created_at":"2026-07-29T01:26:03.047077+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTSCKTPT","created_at":"2026-07-29T01:26:03.047077+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/NTSCKTPT2KFFJXGTG56UIQYLDK","json":"https://pith.science/pith/NTSCKTPT2KFFJXGTG56UIQYLDK.json","graph_json":"https://pith.science/api/pith-number/NTSCKTPT2KFFJXGTG56UIQYLDK/graph.json","events_json":"https://pith.science/api/pith-number/NTSCKTPT2KFFJXGTG56UIQYLDK/events.json","paper":"https://pith.science/paper/NTSCKTPT"},"agent_actions":{"view_html":"https://pith.science/pith/NTSCKTPT2KFFJXGTG56UIQYLDK","download_json":"https://pith.science/pith/NTSCKTPT2KFFJXGTG56UIQYLDK.json","view_paper":"https://pith.science/paper/NTSCKTPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25794&json=true","fetch_graph":"https://pith.science/api/pith-number/NTSCKTPT2KFFJXGTG56UIQYLDK/graph.json","fetch_events":"https://pith.science/api/pith-number/NTSCKTPT2KFFJXGTG56UIQYLDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTSCKTPT2KFFJXGTG56UIQYLDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTSCKTPT2KFFJXGTG56UIQYLDK/action/storage_attestation","attest_author":"https://pith.science/pith/NTSCKTPT2KFFJXGTG56UIQYLDK/action/author_attestation","sign_citation":"https://pith.science/pith/NTSCKTPT2KFFJXGTG56UIQYLDK/action/citation_signature","submit_replication":"https://pith.science/pith/NTSCKTPT2KFFJXGTG56UIQYLDK/action/replication_record"}},"created_at":"2026-07-29T01:26:03.047077+00:00","updated_at":"2026-07-29T01:26:03.047077+00:00"}