{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WTHIJB6X4GTB3ZKWZTCYPASV45","short_pith_number":"pith:WTHIJB6X","schema_version":"1.0","canonical_sha256":"b4ce8487d7e1a61de556ccc5878255e76f535eecb083fc2e35d47669147f230a","source":{"kind":"arxiv","id":"2605.20892","version":1},"attestation_state":"computed","paper":{"title":"FruitEnsemble: MLLM-Guided Arbitration for Heterogeneous ensemble in Fine-Grained Fruit Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhui Yu, Jialu Li, Junhui Li, Ruitong Lu, Youshan Zhang","submitted_at":"2026-05-20T08:31:14Z","abstract_excerpt":"Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-quality datasets and the high visual similarity between classes. To address these challenges, we first constructed a comprehensive dataset comprising 306 fruit categories with 116,233 samples. Moreover, we propose FruitEnsemble, a practical two-stage dynamic inference framework designed to overcome the generalization limitations of static single-model architectures. In the first stage, FruitEnsemble employs a validation-calibrated weighted ensemb"},"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":"2605.20892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T08:31:14Z","cross_cats_sorted":[],"title_canon_sha256":"4e4fb6575a805e91b6599095594037e0feb7de14e320ebd3fa7eda4e0a1c5c76","abstract_canon_sha256":"ba7a038ce2bf4a501ff37ceda9b0276e692fcf46bf88a59194f07de18819c148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:26.728009Z","signature_b64":"CwWk4YhajHRMf/7wqVGR4RHEuN0uVGXlBzSATF+7Bk+h/Rxv2xxPpGFxw7pvDZg42nao3669zxp6uzavt4IHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4ce8487d7e1a61de556ccc5878255e76f535eecb083fc2e35d47669147f230a","last_reissued_at":"2026-05-21T01:05:26.727228Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:26.727228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FruitEnsemble: MLLM-Guided Arbitration for Heterogeneous ensemble in Fine-Grained Fruit Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhui Yu, Jialu Li, Junhui Li, Ruitong Lu, Youshan Zhang","submitted_at":"2026-05-20T08:31:14Z","abstract_excerpt":"Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-quality datasets and the high visual similarity between classes. To address these challenges, we first constructed a comprehensive dataset comprising 306 fruit categories with 116,233 samples. Moreover, we propose FruitEnsemble, a practical two-stage dynamic inference framework designed to overcome the generalization limitations of static single-model architectures. In the first stage, FruitEnsemble employs a validation-calibrated weighted ensemb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20892","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/2605.20892/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":"2605.20892","created_at":"2026-05-21T01:05:26.727373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20892v1","created_at":"2026-05-21T01:05:26.727373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20892","created_at":"2026-05-21T01:05:26.727373+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTHIJB6X4GTB","created_at":"2026-05-21T01:05:26.727373+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTHIJB6X4GTB3ZKW","created_at":"2026-05-21T01:05:26.727373+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTHIJB6X","created_at":"2026-05-21T01:05:26.727373+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/WTHIJB6X4GTB3ZKWZTCYPASV45","json":"https://pith.science/pith/WTHIJB6X4GTB3ZKWZTCYPASV45.json","graph_json":"https://pith.science/api/pith-number/WTHIJB6X4GTB3ZKWZTCYPASV45/graph.json","events_json":"https://pith.science/api/pith-number/WTHIJB6X4GTB3ZKWZTCYPASV45/events.json","paper":"https://pith.science/paper/WTHIJB6X"},"agent_actions":{"view_html":"https://pith.science/pith/WTHIJB6X4GTB3ZKWZTCYPASV45","download_json":"https://pith.science/pith/WTHIJB6X4GTB3ZKWZTCYPASV45.json","view_paper":"https://pith.science/paper/WTHIJB6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20892&json=true","fetch_graph":"https://pith.science/api/pith-number/WTHIJB6X4GTB3ZKWZTCYPASV45/graph.json","fetch_events":"https://pith.science/api/pith-number/WTHIJB6X4GTB3ZKWZTCYPASV45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTHIJB6X4GTB3ZKWZTCYPASV45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTHIJB6X4GTB3ZKWZTCYPASV45/action/storage_attestation","attest_author":"https://pith.science/pith/WTHIJB6X4GTB3ZKWZTCYPASV45/action/author_attestation","sign_citation":"https://pith.science/pith/WTHIJB6X4GTB3ZKWZTCYPASV45/action/citation_signature","submit_replication":"https://pith.science/pith/WTHIJB6X4GTB3ZKWZTCYPASV45/action/replication_record"}},"created_at":"2026-05-21T01:05:26.727373+00:00","updated_at":"2026-05-21T01:05:26.727373+00:00"}