{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:57GCBNONSITZCF7DBQ77DVPW73","short_pith_number":"pith:57GCBNON","schema_version":"1.0","canonical_sha256":"efcc20b5cd92279117e30c3ff1d5f6fefad5d1652dfc7b3b48f226be77076e37","source":{"kind":"arxiv","id":"2607.20523","version":1},"attestation_state":"computed","paper":{"title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"q-bio.QM","authors_text":"Ba Hung Ngo, Cuong D. Do, Mai Phuong Tran, Phuc H. Nguyen, Van-Dinh Nguyen","submitted_at":"2026-07-09T06:30:11Z","abstract_excerpt":"Fine-grained recognition of aquatic species is challenging due to subtle morphological differences and long-tailed distributions, where ultra-rare species are underrepresented. A natural solution is to jointly model segmentation, morphological traits, and species classification within a multi-task learning (MTL) framework. However, existing MTL methods suffer from negative transfer caused by gradient conflicts between low-level dense tasks and high-level classification objectives, degrading fine-grained representations. To address this limitation, we identify gradient interference across hiera"},"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":"2607.20523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-07-09T06:30:11Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"3452f750bd045611876cb3a22031ff0f4e131f7fa9c6ee03fb0d9f02d9270d79","abstract_canon_sha256":"8ce0f7196a276182b61b21e7281a823c253ed9c340bd77d47392a62d2e7cff28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:20.326505Z","signature_b64":"B1JiognpfIL2ztGRujjkUaD54uLPb7sAPylx0R8nsmXJxKJHjVIUeOtS57xFBkTxKeN+F388UsK41rz8bv/YCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efcc20b5cd92279117e30c3ff1d5f6fefad5d1652dfc7b3b48f226be77076e37","last_reissued_at":"2026-07-24T00:23:20.325634Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:20.325634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"q-bio.QM","authors_text":"Ba Hung Ngo, Cuong D. Do, Mai Phuong Tran, Phuc H. Nguyen, Van-Dinh Nguyen","submitted_at":"2026-07-09T06:30:11Z","abstract_excerpt":"Fine-grained recognition of aquatic species is challenging due to subtle morphological differences and long-tailed distributions, where ultra-rare species are underrepresented. A natural solution is to jointly model segmentation, morphological traits, and species classification within a multi-task learning (MTL) framework. However, existing MTL methods suffer from negative transfer caused by gradient conflicts between low-level dense tasks and high-level classification objectives, degrading fine-grained representations. To address this limitation, we identify gradient interference across hiera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20523","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/2607.20523/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":"2607.20523","created_at":"2026-07-24T00:23:20.326081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20523v1","created_at":"2026-07-24T00:23:20.326081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20523","created_at":"2026-07-24T00:23:20.326081+00:00"},{"alias_kind":"pith_short_12","alias_value":"57GCBNONSITZ","created_at":"2026-07-24T00:23:20.326081+00:00"},{"alias_kind":"pith_short_16","alias_value":"57GCBNONSITZCF7D","created_at":"2026-07-24T00:23:20.326081+00:00"},{"alias_kind":"pith_short_8","alias_value":"57GCBNON","created_at":"2026-07-24T00:23:20.326081+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/57GCBNONSITZCF7DBQ77DVPW73","json":"https://pith.science/pith/57GCBNONSITZCF7DBQ77DVPW73.json","graph_json":"https://pith.science/api/pith-number/57GCBNONSITZCF7DBQ77DVPW73/graph.json","events_json":"https://pith.science/api/pith-number/57GCBNONSITZCF7DBQ77DVPW73/events.json","paper":"https://pith.science/paper/57GCBNON"},"agent_actions":{"view_html":"https://pith.science/pith/57GCBNONSITZCF7DBQ77DVPW73","download_json":"https://pith.science/pith/57GCBNONSITZCF7DBQ77DVPW73.json","view_paper":"https://pith.science/paper/57GCBNON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20523&json=true","fetch_graph":"https://pith.science/api/pith-number/57GCBNONSITZCF7DBQ77DVPW73/graph.json","fetch_events":"https://pith.science/api/pith-number/57GCBNONSITZCF7DBQ77DVPW73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57GCBNONSITZCF7DBQ77DVPW73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57GCBNONSITZCF7DBQ77DVPW73/action/storage_attestation","attest_author":"https://pith.science/pith/57GCBNONSITZCF7DBQ77DVPW73/action/author_attestation","sign_citation":"https://pith.science/pith/57GCBNONSITZCF7DBQ77DVPW73/action/citation_signature","submit_replication":"https://pith.science/pith/57GCBNONSITZCF7DBQ77DVPW73/action/replication_record"}},"created_at":"2026-07-24T00:23:20.326081+00:00","updated_at":"2026-07-24T00:23:20.326081+00:00"}