{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2Q6GOGGEUGZI2WVEGNS7GKVHTH","short_pith_number":"pith:2Q6GOGGE","schema_version":"1.0","canonical_sha256":"d43c6718c4a1b28d5aa43365f32aa799e03f0952e0b5fb89bcd0150ffab6d66a","source":{"kind":"arxiv","id":"2605.16383","version":1},"attestation_state":"computed","paper":{"title":"A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ezel Kilicdere, Fabio Cuzzolin, Shireen Kudukkil Manchingal","submitted_at":"2026-05-11T09:43:43Z","abstract_excerpt":"Deep neural networks achieve high accuracy on image classification tasks. Yet, they often produce overconfident predictions as which fail to express epistemic uncertainty, and frequently violate logical or structural constraints present in the data. These limitations are particularly pronounced in hierarchical classification, where predictions across fine and coarse levels must remain coherent. We propose, for the first time, a unified neurosymbolic and epistemic modelling framework that augments Swin Transformers with focal set reasoning and differentiable fuzzy logic. Rather than treating la"},"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":"2605.16383","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T09:43:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"237135f9c39401a7ea4945c231c7cf2ccf794d554f7da5c5e2209a9325c72d49","abstract_canon_sha256":"680a77a7d56220111632e8c8bf2a2abe41b61dac7c93d3b765e508410f98d297"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:19.435218Z","signature_b64":"cNuOJepKNTIdfunhKDZekUuY4dXTMT4QLTofE+PCVr7daOH7kkxzftny8D0roy61IkjbWtsvvNGy0QSlSkBVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d43c6718c4a1b28d5aa43365f32aa799e03f0952e0b5fb89bcd0150ffab6d66a","last_reissued_at":"2026-05-20T00:02:19.434477Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:19.434477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ezel Kilicdere, Fabio Cuzzolin, Shireen Kudukkil Manchingal","submitted_at":"2026-05-11T09:43:43Z","abstract_excerpt":"Deep neural networks achieve high accuracy on image classification tasks. Yet, they often produce overconfident predictions as which fail to express epistemic uncertainty, and frequently violate logical or structural constraints present in the data. These limitations are particularly pronounced in hierarchical classification, where predictions across fine and coarse levels must remain coherent. We propose, for the first time, a unified neurosymbolic and epistemic modelling framework that augments Swin Transformers with focal set reasoning and differentiable fuzzy logic. Rather than treating la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16383","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/2605.16383/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.612638Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"98f21d7036f432b748be8876d27d291bd35f7f9287b93e7333ab356443accafc"},"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":"2605.16383","created_at":"2026-05-20T00:02:19.434596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16383v1","created_at":"2026-05-20T00:02:19.434596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16383","created_at":"2026-05-20T00:02:19.434596+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Q6GOGGEUGZI","created_at":"2026-05-20T00:02:19.434596+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Q6GOGGEUGZI2WVE","created_at":"2026-05-20T00:02:19.434596+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Q6GOGGE","created_at":"2026-05-20T00:02:19.434596+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/2Q6GOGGEUGZI2WVEGNS7GKVHTH","json":"https://pith.science/pith/2Q6GOGGEUGZI2WVEGNS7GKVHTH.json","graph_json":"https://pith.science/api/pith-number/2Q6GOGGEUGZI2WVEGNS7GKVHTH/graph.json","events_json":"https://pith.science/api/pith-number/2Q6GOGGEUGZI2WVEGNS7GKVHTH/events.json","paper":"https://pith.science/paper/2Q6GOGGE"},"agent_actions":{"view_html":"https://pith.science/pith/2Q6GOGGEUGZI2WVEGNS7GKVHTH","download_json":"https://pith.science/pith/2Q6GOGGEUGZI2WVEGNS7GKVHTH.json","view_paper":"https://pith.science/paper/2Q6GOGGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16383&json=true","fetch_graph":"https://pith.science/api/pith-number/2Q6GOGGEUGZI2WVEGNS7GKVHTH/graph.json","fetch_events":"https://pith.science/api/pith-number/2Q6GOGGEUGZI2WVEGNS7GKVHTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Q6GOGGEUGZI2WVEGNS7GKVHTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Q6GOGGEUGZI2WVEGNS7GKVHTH/action/storage_attestation","attest_author":"https://pith.science/pith/2Q6GOGGEUGZI2WVEGNS7GKVHTH/action/author_attestation","sign_citation":"https://pith.science/pith/2Q6GOGGEUGZI2WVEGNS7GKVHTH/action/citation_signature","submit_replication":"https://pith.science/pith/2Q6GOGGEUGZI2WVEGNS7GKVHTH/action/replication_record"}},"created_at":"2026-05-20T00:02:19.434596+00:00","updated_at":"2026-05-20T00:02:19.434596+00:00"}