{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5SWBIWTHJQ4SRM6DPE5N2UVD4J","short_pith_number":"pith:5SWBIWTH","schema_version":"1.0","canonical_sha256":"ecac145a674c3928b3c3793add52a3e26df73c99ce7519a16fb6f51a7e82cdac","source":{"kind":"arxiv","id":"2411.16438","version":1},"attestation_state":"computed","paper":{"title":"Harnessing Superclasses for Learning from Hierarchical Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Leonardo Tanzi (Polito), Nicolas Urbani (Heudiasyc), Sylvain Rousseau (Heudiasyc), Yves Grandvalet (Heudiasyc)","submitted_at":"2024-11-25T14:39:52Z","abstract_excerpt":"In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree expressing the inclusion of classes in superclasses. We introduce a loss for this type of supervised hierarchical classification. It utilizes the knowledge of the hierarchy to assign each example not only to a class but also to all encompassing superclasses. Applicable to any feedforward architecture with a softmax output layer, this loss is a proper scoring rule, in that its expectation is minimized by the true posterior class probabilities. This property allows us to simul"},"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":"2411.16438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T14:39:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dffb2c4014b00212dd4799d0d0bdb627ff429562dc7477278fdb421207cda669","abstract_canon_sha256":"0f521e839c6576fc3db058fa2cfca9fd5fc99c648a5ffe65c835c9b8913fe021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:09.403280Z","signature_b64":"z/oNc5S2OhxP+kCk+rVCONtoRHqYVLG3p8BWLsOdRuFo/YrOxE0WT2PdubNYKPYQyOh3g7TKIXXZxISfDMNmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecac145a674c3928b3c3793add52a3e26df73c99ce7519a16fb6f51a7e82cdac","last_reissued_at":"2026-07-05T09:40:09.402840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:09.402840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Superclasses for Learning from Hierarchical Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Leonardo Tanzi (Polito), Nicolas Urbani (Heudiasyc), Sylvain Rousseau (Heudiasyc), Yves Grandvalet (Heudiasyc)","submitted_at":"2024-11-25T14:39:52Z","abstract_excerpt":"In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree expressing the inclusion of classes in superclasses. We introduce a loss for this type of supervised hierarchical classification. It utilizes the knowledge of the hierarchy to assign each example not only to a class but also to all encompassing superclasses. Applicable to any feedforward architecture with a softmax output layer, this loss is a proper scoring rule, in that its expectation is minimized by the true posterior class probabilities. This property allows us to simul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16438","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/2411.16438/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":"2411.16438","created_at":"2026-07-05T09:40:09.402897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16438v1","created_at":"2026-07-05T09:40:09.402897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16438","created_at":"2026-07-05T09:40:09.402897+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SWBIWTHJQ4S","created_at":"2026-07-05T09:40:09.402897+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SWBIWTHJQ4SRM6D","created_at":"2026-07-05T09:40:09.402897+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SWBIWTH","created_at":"2026-07-05T09:40:09.402897+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/5SWBIWTHJQ4SRM6DPE5N2UVD4J","json":"https://pith.science/pith/5SWBIWTHJQ4SRM6DPE5N2UVD4J.json","graph_json":"https://pith.science/api/pith-number/5SWBIWTHJQ4SRM6DPE5N2UVD4J/graph.json","events_json":"https://pith.science/api/pith-number/5SWBIWTHJQ4SRM6DPE5N2UVD4J/events.json","paper":"https://pith.science/paper/5SWBIWTH"},"agent_actions":{"view_html":"https://pith.science/pith/5SWBIWTHJQ4SRM6DPE5N2UVD4J","download_json":"https://pith.science/pith/5SWBIWTHJQ4SRM6DPE5N2UVD4J.json","view_paper":"https://pith.science/paper/5SWBIWTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16438&json=true","fetch_graph":"https://pith.science/api/pith-number/5SWBIWTHJQ4SRM6DPE5N2UVD4J/graph.json","fetch_events":"https://pith.science/api/pith-number/5SWBIWTHJQ4SRM6DPE5N2UVD4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SWBIWTHJQ4SRM6DPE5N2UVD4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SWBIWTHJQ4SRM6DPE5N2UVD4J/action/storage_attestation","attest_author":"https://pith.science/pith/5SWBIWTHJQ4SRM6DPE5N2UVD4J/action/author_attestation","sign_citation":"https://pith.science/pith/5SWBIWTHJQ4SRM6DPE5N2UVD4J/action/citation_signature","submit_replication":"https://pith.science/pith/5SWBIWTHJQ4SRM6DPE5N2UVD4J/action/replication_record"}},"created_at":"2026-07-05T09:40:09.402897+00:00","updated_at":"2026-07-05T09:40:09.402897+00:00"}