{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WMK76ISPDPKUWHUKEUWTQGRVQB","short_pith_number":"pith:WMK76ISP","schema_version":"1.0","canonical_sha256":"b315ff224f1bd54b1e8a252d381a35806225236122d119b8f31818a54f7df977","source":{"kind":"arxiv","id":"2506.23247","version":1},"attestation_state":"computed","paper":{"title":"Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Martens, James Hinns","submitted_at":"2025-06-29T14:11:02Z","abstract_excerpt":"Deep learning dominates image classification tasks, yet understanding how models arrive at predictions remains a challenge. Much research focuses on local explanations of individual predictions, such as saliency maps, which visualise the influence of specific pixels on a model's prediction. However, reviewing many of these explanations to identify recurring patterns is infeasible, while global methods often oversimplify and miss important local behaviours. To address this, we propose Segment Attribution Tables (SATs), a method for summarising local saliency explanations into (semi-)global insi"},"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":"2506.23247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T14:11:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0f84946cb2386a57668457a03b7ece7cc6bcc6673bc138850f8f7459ca2f93e2","abstract_canon_sha256":"e06c420874ca5ec11d8e242e4f5c22b45864bdbf663384e4a9f30afe5b119d2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:18.538494Z","signature_b64":"LWcf+jsIibZNw/ftZbDGn8p7UaBPc9RPkj8E2+z0Ph2oXGYUe3+cBcufRepAzqI1d943PGQ+C3uKDOg/q7VqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b315ff224f1bd54b1e8a252d381a35806225236122d119b8f31818a54f7df977","last_reissued_at":"2026-07-05T11:29:18.537939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:18.537939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Martens, James Hinns","submitted_at":"2025-06-29T14:11:02Z","abstract_excerpt":"Deep learning dominates image classification tasks, yet understanding how models arrive at predictions remains a challenge. Much research focuses on local explanations of individual predictions, such as saliency maps, which visualise the influence of specific pixels on a model's prediction. However, reviewing many of these explanations to identify recurring patterns is infeasible, while global methods often oversimplify and miss important local behaviours. To address this, we propose Segment Attribution Tables (SATs), a method for summarising local saliency explanations into (semi-)global insi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23247","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/2506.23247/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":"2506.23247","created_at":"2026-07-05T11:29:18.538009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23247v1","created_at":"2026-07-05T11:29:18.538009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23247","created_at":"2026-07-05T11:29:18.538009+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMK76ISPDPKU","created_at":"2026-07-05T11:29:18.538009+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMK76ISPDPKUWHUK","created_at":"2026-07-05T11:29:18.538009+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMK76ISP","created_at":"2026-07-05T11:29:18.538009+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/WMK76ISPDPKUWHUKEUWTQGRVQB","json":"https://pith.science/pith/WMK76ISPDPKUWHUKEUWTQGRVQB.json","graph_json":"https://pith.science/api/pith-number/WMK76ISPDPKUWHUKEUWTQGRVQB/graph.json","events_json":"https://pith.science/api/pith-number/WMK76ISPDPKUWHUKEUWTQGRVQB/events.json","paper":"https://pith.science/paper/WMK76ISP"},"agent_actions":{"view_html":"https://pith.science/pith/WMK76ISPDPKUWHUKEUWTQGRVQB","download_json":"https://pith.science/pith/WMK76ISPDPKUWHUKEUWTQGRVQB.json","view_paper":"https://pith.science/paper/WMK76ISP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23247&json=true","fetch_graph":"https://pith.science/api/pith-number/WMK76ISPDPKUWHUKEUWTQGRVQB/graph.json","fetch_events":"https://pith.science/api/pith-number/WMK76ISPDPKUWHUKEUWTQGRVQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMK76ISPDPKUWHUKEUWTQGRVQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMK76ISPDPKUWHUKEUWTQGRVQB/action/storage_attestation","attest_author":"https://pith.science/pith/WMK76ISPDPKUWHUKEUWTQGRVQB/action/author_attestation","sign_citation":"https://pith.science/pith/WMK76ISPDPKUWHUKEUWTQGRVQB/action/citation_signature","submit_replication":"https://pith.science/pith/WMK76ISPDPKUWHUKEUWTQGRVQB/action/replication_record"}},"created_at":"2026-07-05T11:29:18.538009+00:00","updated_at":"2026-07-05T11:29:18.538009+00:00"}