{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O7YZYLPUXLD4SED7N2KCJ72TY4","short_pith_number":"pith:O7YZYLPU","schema_version":"1.0","canonical_sha256":"77f19c2df4bac7c9107f6e9424ff53c72eec97de0f5881a355ec6dfe17df36a7","source":{"kind":"arxiv","id":"2107.00808","version":1},"attestation_state":"computed","paper":{"title":"MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weiping Wang, Xiaoni Li, Yucan Zhou, Yu Zhou","submitted_at":"2021-07-02T02:53:35Z","abstract_excerpt":"Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes. As the label structure decides its performance, many existing approaches attempt to construct an excellent label structure for promoting the classification results. In this paper, we consider that different label structures provide a variety of prior knowledge for category recognition, thus fusing them is helpful to achieve better hierarchical classification results. Furthermore, we propose a multi-task multi-structure fusion model to integrate different label s"},"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":"2107.00808","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-02T02:53:35Z","cross_cats_sorted":[],"title_canon_sha256":"c71ee943bc0ff2ca6d81b59e080f0df4f04da062681f3760f9ec72a67edda2bd","abstract_canon_sha256":"c084a94b827c36fc10ac5239ce5bc4c6371a4d73310ea853b4ad490c8e0cd32c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:33.912703Z","signature_b64":"3reDBz7e7v3X3z9MjdpwK6OzNlrhqTvtAAdSRh8KWintMDKKKZXUBmJw3KUAdSl5UJwPnrKSghdCFvu8jL6/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77f19c2df4bac7c9107f6e9424ff53c72eec97de0f5881a355ec6dfe17df36a7","last_reissued_at":"2026-07-05T02:54:33.912379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:33.912379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weiping Wang, Xiaoni Li, Yucan Zhou, Yu Zhou","submitted_at":"2021-07-02T02:53:35Z","abstract_excerpt":"Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes. As the label structure decides its performance, many existing approaches attempt to construct an excellent label structure for promoting the classification results. In this paper, we consider that different label structures provide a variety of prior knowledge for category recognition, thus fusing them is helpful to achieve better hierarchical classification results. Furthermore, we propose a multi-task multi-structure fusion model to integrate different label s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00808","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/2107.00808/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":"2107.00808","created_at":"2026-07-05T02:54:33.912431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00808v1","created_at":"2026-07-05T02:54:33.912431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00808","created_at":"2026-07-05T02:54:33.912431+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7YZYLPUXLD4","created_at":"2026-07-05T02:54:33.912431+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7YZYLPUXLD4SED7","created_at":"2026-07-05T02:54:33.912431+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7YZYLPU","created_at":"2026-07-05T02:54:33.912431+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/O7YZYLPUXLD4SED7N2KCJ72TY4","json":"https://pith.science/pith/O7YZYLPUXLD4SED7N2KCJ72TY4.json","graph_json":"https://pith.science/api/pith-number/O7YZYLPUXLD4SED7N2KCJ72TY4/graph.json","events_json":"https://pith.science/api/pith-number/O7YZYLPUXLD4SED7N2KCJ72TY4/events.json","paper":"https://pith.science/paper/O7YZYLPU"},"agent_actions":{"view_html":"https://pith.science/pith/O7YZYLPUXLD4SED7N2KCJ72TY4","download_json":"https://pith.science/pith/O7YZYLPUXLD4SED7N2KCJ72TY4.json","view_paper":"https://pith.science/paper/O7YZYLPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00808&json=true","fetch_graph":"https://pith.science/api/pith-number/O7YZYLPUXLD4SED7N2KCJ72TY4/graph.json","fetch_events":"https://pith.science/api/pith-number/O7YZYLPUXLD4SED7N2KCJ72TY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7YZYLPUXLD4SED7N2KCJ72TY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7YZYLPUXLD4SED7N2KCJ72TY4/action/storage_attestation","attest_author":"https://pith.science/pith/O7YZYLPUXLD4SED7N2KCJ72TY4/action/author_attestation","sign_citation":"https://pith.science/pith/O7YZYLPUXLD4SED7N2KCJ72TY4/action/citation_signature","submit_replication":"https://pith.science/pith/O7YZYLPUXLD4SED7N2KCJ72TY4/action/replication_record"}},"created_at":"2026-07-05T02:54:33.912431+00:00","updated_at":"2026-07-05T02:54:33.912431+00:00"}