{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CIPZ5H2H35VNSC5ZHLLMSV6VXG","short_pith_number":"pith:CIPZ5H2H","schema_version":"1.0","canonical_sha256":"121f9e9f47df6ad90bb93ad6c957d5b9894cc6acfcd99dc9c90c1523adc85f9b","source":{"kind":"arxiv","id":"2607.28148","version":1},"attestation_state":"computed","paper":{"title":"What Makes Deep Learning Work for Traditional Chinese Medicine Tongue Diagnosis? A Comprehensive Ablation Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanqing Zhao, Junze Geng, Linan Wang, Longxia Gao, Meng Zhang, Yuhe Han","submitted_at":"2026-07-30T12:55:05Z","abstract_excerpt":"Deep learning has shown promise for automated tongue diagnosis in traditional Chinese medicine (TCM), yet the design space remains underexplored. We conducted a systematic ablation study spanning 20+ model versions under rigorous 5-fold cross-validation on TongueDx2 (5,109 images, 976 expert-annotated) and a merged dataset of 11,101 samples. We compared six backbone architectures, four loss functions, five augmentation strategies, and six training strategies. The best 976-sample model achieved weighted-F1 of 0.6625 using ConvNeXt-Tiny with restrained augmentation and weak-group ensemble, while"},"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":"2607.28148","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T12:55:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed41488c9d2ef79a323b6b325b91e19188a0655b0f0e395f740467d7629af1ed","abstract_canon_sha256":"0c9927c764beba10e8c46022fbfb4e90f845b5ffd99de903bbf96ec0c6056ba6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"121f9e9f47df6ad90bb93ad6c957d5b9894cc6acfcd99dc9c90c1523adc85f9b","last_reissued_at":"2026-07-31T01:35:52.594630Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:52.594630Z"},"graph_snapshot":{"paper":{"title":"What Makes Deep Learning Work for Traditional Chinese Medicine Tongue Diagnosis? A Comprehensive Ablation Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanqing Zhao, Junze Geng, Linan Wang, Longxia Gao, Meng Zhang, Yuhe Han","submitted_at":"2026-07-30T12:55:05Z","abstract_excerpt":"Deep learning has shown promise for automated tongue diagnosis in traditional Chinese medicine (TCM), yet the design space remains underexplored. We conducted a systematic ablation study spanning 20+ model versions under rigorous 5-fold cross-validation on TongueDx2 (5,109 images, 976 expert-annotated) and a merged dataset of 11,101 samples. We compared six backbone architectures, four loss functions, five augmentation strategies, and six training strategies. The best 976-sample model achieved weighted-F1 of 0.6625 using ConvNeXt-Tiny with restrained augmentation and weak-group ensemble, while"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28148","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/2607.28148/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":"2607.28148","created_at":"2026-07-31T01:35:52.597700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28148v1","created_at":"2026-07-31T01:35:52.597700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28148","created_at":"2026-07-31T01:35:52.597700+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIPZ5H2H35VN","created_at":"2026-07-31T01:35:52.597700+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIPZ5H2H35VNSC5Z","created_at":"2026-07-31T01:35:52.597700+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIPZ5H2H","created_at":"2026-07-31T01:35:52.597700+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/CIPZ5H2H35VNSC5ZHLLMSV6VXG","json":"https://pith.science/pith/CIPZ5H2H35VNSC5ZHLLMSV6VXG.json","graph_json":"https://pith.science/api/pith-number/CIPZ5H2H35VNSC5ZHLLMSV6VXG/graph.json","events_json":"https://pith.science/api/pith-number/CIPZ5H2H35VNSC5ZHLLMSV6VXG/events.json","paper":"https://pith.science/paper/CIPZ5H2H"},"agent_actions":{"view_html":"https://pith.science/pith/CIPZ5H2H35VNSC5ZHLLMSV6VXG","download_json":"https://pith.science/pith/CIPZ5H2H35VNSC5ZHLLMSV6VXG.json","view_paper":"https://pith.science/paper/CIPZ5H2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28148&json=true","fetch_graph":"https://pith.science/api/pith-number/CIPZ5H2H35VNSC5ZHLLMSV6VXG/graph.json","fetch_events":"https://pith.science/api/pith-number/CIPZ5H2H35VNSC5ZHLLMSV6VXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIPZ5H2H35VNSC5ZHLLMSV6VXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIPZ5H2H35VNSC5ZHLLMSV6VXG/action/storage_attestation","attest_author":"https://pith.science/pith/CIPZ5H2H35VNSC5ZHLLMSV6VXG/action/author_attestation","sign_citation":"https://pith.science/pith/CIPZ5H2H35VNSC5ZHLLMSV6VXG/action/citation_signature","submit_replication":"https://pith.science/pith/CIPZ5H2H35VNSC5ZHLLMSV6VXG/action/replication_record"}},"created_at":"2026-07-31T01:35:52.597700+00:00","updated_at":"2026-07-31T01:35:52.597700+00:00"}