{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:62X2WCFGW3GEPME56WXM2DQ7HG","short_pith_number":"pith:62X2WCFG","schema_version":"1.0","canonical_sha256":"f6afab08a6b6cc47b09df5aecd0e1f3982b7ae29e6abb7684cf8a93b973f536d","source":{"kind":"arxiv","id":"2502.01048","version":1},"attestation_state":"computed","paper":{"title":"Sparks of Explainability: Recent Advancements in Explaining Large Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Thomas Fel","submitted_at":"2025-02-03T04:49:32Z","abstract_excerpt":"This thesis explores advanced approaches to improve explainability in computer vision by analyzing and modeling the features exploited by deep neural networks. Initially, it evaluates attribution methods, notably saliency maps, by introducing a metric based on algorithmic stability and an approach utilizing Sobol indices, which, through quasi-Monte Carlo sequences, allows a significant reduction in computation time. In addition, the EVA method offers a first formulation of attribution with formal guarantees via verified perturbation analysis.\n  Experimental results indicate that in complex sce"},"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":"2502.01048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T04:49:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebce7309cd1636e0e31f5aad13c33b936ffd229b93d4c694b6e9de33ac001a8b","abstract_canon_sha256":"4e4663c81222df32042f428d0902db4d060c6715cd493e8429d0bbd3a3960d12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:42.208468Z","signature_b64":"pBD6cjvutw21XNmEKJ/vV8Hl89eukIDb44tfSpgRMEB2R5SOWzxaP4zPQgxfzE2BzLoRxgBkrkk9V6T0opx1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6afab08a6b6cc47b09df5aecd0e1f3982b7ae29e6abb7684cf8a93b973f536d","last_reissued_at":"2026-07-05T10:08:42.208042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:42.208042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparks of Explainability: Recent Advancements in Explaining Large Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Thomas Fel","submitted_at":"2025-02-03T04:49:32Z","abstract_excerpt":"This thesis explores advanced approaches to improve explainability in computer vision by analyzing and modeling the features exploited by deep neural networks. Initially, it evaluates attribution methods, notably saliency maps, by introducing a metric based on algorithmic stability and an approach utilizing Sobol indices, which, through quasi-Monte Carlo sequences, allows a significant reduction in computation time. In addition, the EVA method offers a first formulation of attribution with formal guarantees via verified perturbation analysis.\n  Experimental results indicate that in complex sce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01048","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/2502.01048/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":"2502.01048","created_at":"2026-07-05T10:08:42.208100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01048v1","created_at":"2026-07-05T10:08:42.208100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01048","created_at":"2026-07-05T10:08:42.208100+00:00"},{"alias_kind":"pith_short_12","alias_value":"62X2WCFGW3GE","created_at":"2026-07-05T10:08:42.208100+00:00"},{"alias_kind":"pith_short_16","alias_value":"62X2WCFGW3GEPME5","created_at":"2026-07-05T10:08:42.208100+00:00"},{"alias_kind":"pith_short_8","alias_value":"62X2WCFG","created_at":"2026-07-05T10:08:42.208100+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/62X2WCFGW3GEPME56WXM2DQ7HG","json":"https://pith.science/pith/62X2WCFGW3GEPME56WXM2DQ7HG.json","graph_json":"https://pith.science/api/pith-number/62X2WCFGW3GEPME56WXM2DQ7HG/graph.json","events_json":"https://pith.science/api/pith-number/62X2WCFGW3GEPME56WXM2DQ7HG/events.json","paper":"https://pith.science/paper/62X2WCFG"},"agent_actions":{"view_html":"https://pith.science/pith/62X2WCFGW3GEPME56WXM2DQ7HG","download_json":"https://pith.science/pith/62X2WCFGW3GEPME56WXM2DQ7HG.json","view_paper":"https://pith.science/paper/62X2WCFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01048&json=true","fetch_graph":"https://pith.science/api/pith-number/62X2WCFGW3GEPME56WXM2DQ7HG/graph.json","fetch_events":"https://pith.science/api/pith-number/62X2WCFGW3GEPME56WXM2DQ7HG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62X2WCFGW3GEPME56WXM2DQ7HG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62X2WCFGW3GEPME56WXM2DQ7HG/action/storage_attestation","attest_author":"https://pith.science/pith/62X2WCFGW3GEPME56WXM2DQ7HG/action/author_attestation","sign_citation":"https://pith.science/pith/62X2WCFGW3GEPME56WXM2DQ7HG/action/citation_signature","submit_replication":"https://pith.science/pith/62X2WCFGW3GEPME56WXM2DQ7HG/action/replication_record"}},"created_at":"2026-07-05T10:08:42.208100+00:00","updated_at":"2026-07-05T10:08:42.208100+00:00"}