{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FTVKBQCQKNWGSQVGN3A522SIYL","short_pith_number":"pith:FTVKBQCQ","schema_version":"1.0","canonical_sha256":"2ceaa0c050536c6942a66ec1dd6a48c2cf07c346bf66973be0ae799bc86ac1cd","source":{"kind":"arxiv","id":"2107.00456","version":2},"attestation_state":"computed","paper":{"title":"Crowdsourcing Evaluation of Saliency-based XAI Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.HC","authors_text":"Arseny Tolmachev, Hisashi Kashima, Koh Takeuchi, Koji Maruhashi, Seiji Okajima, Tatsuya Yamamoto, Tomoyoshi Takebayashi, Xiaotian Lu","submitted_at":"2021-06-27T17:37:53Z","abstract_excerpt":"Understanding the reasons behind the predictions made by deep neural networks is critical for gaining human trust in many important applications, which is reflected in the increasing demand for explainability in AI (XAI) in recent years. Saliency-based feature attribution methods, which highlight important parts of images that contribute to decisions by classifiers, are often used as XAI methods, especially in the field of computer vision. In order to compare various saliency-based XAI methods quantitatively, several approaches for automated evaluation schemes have been proposed; however, ther"},"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":"2107.00456","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2021-06-27T17:37:53Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a3f0eb2820e2f27a44e9311a731f788bf86f9e5aa3b3f6c7532419661b2fb758","abstract_canon_sha256":"aefb13812300fe97af48b2b81dc85d00609c4f9213bf761c037683068b2efad4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:46.580174Z","signature_b64":"KP5HTGz+dS24xKIwN+niu9YWZt50A+sRzmYE6OjPf+HFW29ChvKSNTELycRBI6gPfEwUxaP+yPB5bssh8yARAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ceaa0c050536c6942a66ec1dd6a48c2cf07c346bf66973be0ae799bc86ac1cd","last_reissued_at":"2026-07-05T03:09:46.579709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:46.579709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crowdsourcing Evaluation of Saliency-based XAI Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.HC","authors_text":"Arseny Tolmachev, Hisashi Kashima, Koh Takeuchi, Koji Maruhashi, Seiji Okajima, Tatsuya Yamamoto, Tomoyoshi Takebayashi, Xiaotian Lu","submitted_at":"2021-06-27T17:37:53Z","abstract_excerpt":"Understanding the reasons behind the predictions made by deep neural networks is critical for gaining human trust in many important applications, which is reflected in the increasing demand for explainability in AI (XAI) in recent years. Saliency-based feature attribution methods, which highlight important parts of images that contribute to decisions by classifiers, are often used as XAI methods, especially in the field of computer vision. In order to compare various saliency-based XAI methods quantitatively, several approaches for automated evaluation schemes have been proposed; however, ther"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00456","kind":"arxiv","version":2},"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/2107.00456/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":"2107.00456","created_at":"2026-07-05T03:09:46.579768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00456v2","created_at":"2026-07-05T03:09:46.579768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00456","created_at":"2026-07-05T03:09:46.579768+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTVKBQCQKNWG","created_at":"2026-07-05T03:09:46.579768+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTVKBQCQKNWGSQVG","created_at":"2026-07-05T03:09:46.579768+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTVKBQCQ","created_at":"2026-07-05T03:09:46.579768+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/FTVKBQCQKNWGSQVGN3A522SIYL","json":"https://pith.science/pith/FTVKBQCQKNWGSQVGN3A522SIYL.json","graph_json":"https://pith.science/api/pith-number/FTVKBQCQKNWGSQVGN3A522SIYL/graph.json","events_json":"https://pith.science/api/pith-number/FTVKBQCQKNWGSQVGN3A522SIYL/events.json","paper":"https://pith.science/paper/FTVKBQCQ"},"agent_actions":{"view_html":"https://pith.science/pith/FTVKBQCQKNWGSQVGN3A522SIYL","download_json":"https://pith.science/pith/FTVKBQCQKNWGSQVGN3A522SIYL.json","view_paper":"https://pith.science/paper/FTVKBQCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00456&json=true","fetch_graph":"https://pith.science/api/pith-number/FTVKBQCQKNWGSQVGN3A522SIYL/graph.json","fetch_events":"https://pith.science/api/pith-number/FTVKBQCQKNWGSQVGN3A522SIYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTVKBQCQKNWGSQVGN3A522SIYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTVKBQCQKNWGSQVGN3A522SIYL/action/storage_attestation","attest_author":"https://pith.science/pith/FTVKBQCQKNWGSQVGN3A522SIYL/action/author_attestation","sign_citation":"https://pith.science/pith/FTVKBQCQKNWGSQVGN3A522SIYL/action/citation_signature","submit_replication":"https://pith.science/pith/FTVKBQCQKNWGSQVGN3A522SIYL/action/replication_record"}},"created_at":"2026-07-05T03:09:46.579768+00:00","updated_at":"2026-07-05T03:09:46.579768+00:00"}