{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NYTFRRIT42TACDYF7FHPUFKBAZ","short_pith_number":"pith:NYTFRRIT","schema_version":"1.0","canonical_sha256":"6e2658c513e6a6010f05f94efa15410643fb435c94d9cf0d4fc74bdb8f9f6b65","source":{"kind":"arxiv","id":"2108.10233","version":1},"attestation_state":"computed","paper":{"title":"Fusion of evidential CNN classifiers for image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Philippe Xu, Thierry Denoeux, Zheng Tong","submitted_at":"2021-08-23T15:12:26Z","abstract_excerpt":"We propose an information-fusion approach based on belief functions to combine convolutional neural networks. In this approach, several pre-trained DS-based CNN architectures extract features from input images and convert them into mass functions on different frames of discernment. A fusion module then aggregates these mass functions using Dempster's rule. An end-to-end learning procedure allows us to fine-tune the overall architecture using a learning set with soft labels, which further improves the classification performance. The effectiveness of this approach is demonstrated experimentally "},"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":"2108.10233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-23T15:12:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30b8cc0a336ae3da76cc70534df1ac324207dfc85758fab310083d230459a84e","abstract_canon_sha256":"9eae8641023d2d15f64c20536a76d338881a055779a5a0ee4486c78e362b634d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:03.678049Z","signature_b64":"E0ExBJz8rKzuqwWc4k0q3KbnikAk7rcSRAKt8ECagcNauRPD6PM2tDseRCzl3aPMv/AqpPJlk9dOSIq/u/FfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e2658c513e6a6010f05f94efa15410643fb435c94d9cf0d4fc74bdb8f9f6b65","last_reissued_at":"2026-07-05T03:08:03.677646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:03.677646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusion of evidential CNN classifiers for image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Philippe Xu, Thierry Denoeux, Zheng Tong","submitted_at":"2021-08-23T15:12:26Z","abstract_excerpt":"We propose an information-fusion approach based on belief functions to combine convolutional neural networks. In this approach, several pre-trained DS-based CNN architectures extract features from input images and convert them into mass functions on different frames of discernment. A fusion module then aggregates these mass functions using Dempster's rule. An end-to-end learning procedure allows us to fine-tune the overall architecture using a learning set with soft labels, which further improves the classification performance. The effectiveness of this approach is demonstrated experimentally "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10233","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/2108.10233/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":"2108.10233","created_at":"2026-07-05T03:08:03.677704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.10233v1","created_at":"2026-07-05T03:08:03.677704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10233","created_at":"2026-07-05T03:08:03.677704+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYTFRRIT42TA","created_at":"2026-07-05T03:08:03.677704+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYTFRRIT42TACDYF","created_at":"2026-07-05T03:08:03.677704+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYTFRRIT","created_at":"2026-07-05T03:08:03.677704+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/NYTFRRIT42TACDYF7FHPUFKBAZ","json":"https://pith.science/pith/NYTFRRIT42TACDYF7FHPUFKBAZ.json","graph_json":"https://pith.science/api/pith-number/NYTFRRIT42TACDYF7FHPUFKBAZ/graph.json","events_json":"https://pith.science/api/pith-number/NYTFRRIT42TACDYF7FHPUFKBAZ/events.json","paper":"https://pith.science/paper/NYTFRRIT"},"agent_actions":{"view_html":"https://pith.science/pith/NYTFRRIT42TACDYF7FHPUFKBAZ","download_json":"https://pith.science/pith/NYTFRRIT42TACDYF7FHPUFKBAZ.json","view_paper":"https://pith.science/paper/NYTFRRIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.10233&json=true","fetch_graph":"https://pith.science/api/pith-number/NYTFRRIT42TACDYF7FHPUFKBAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NYTFRRIT42TACDYF7FHPUFKBAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYTFRRIT42TACDYF7FHPUFKBAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYTFRRIT42TACDYF7FHPUFKBAZ/action/storage_attestation","attest_author":"https://pith.science/pith/NYTFRRIT42TACDYF7FHPUFKBAZ/action/author_attestation","sign_citation":"https://pith.science/pith/NYTFRRIT42TACDYF7FHPUFKBAZ/action/citation_signature","submit_replication":"https://pith.science/pith/NYTFRRIT42TACDYF7FHPUFKBAZ/action/replication_record"}},"created_at":"2026-07-05T03:08:03.677704+00:00","updated_at":"2026-07-05T03:08:03.677704+00:00"}