{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZBBTZWQYEERLVWHAPTUTLWQ6IE","short_pith_number":"pith:ZBBTZWQY","schema_version":"1.0","canonical_sha256":"c8433cda182122bad8e07ce935da1e4104da9fb33001fcea894bb8c5fc10d1a8","source":{"kind":"arxiv","id":"2402.09164","version":3},"attestation_state":"computed","paper":{"title":"Less is More: Fewer Interpretable Region via Submodular Subset Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hua Zhang, Jingzhi Li, Ruoyu Chen, Siyuan Liang, Xiaochun Cao","submitted_at":"2024-02-14T13:30:02Z","abstract_excerpt":"Image attribution algorithms aim to identify important regions that are highly relevant to model decisions. Although existing attribution solutions can effectively assign importance to target elements, they still face the following challenges: 1) existing attribution methods generate inaccurate small regions thus misleading the direction of correct attribution, and 2) the model cannot produce good attribution results for samples with wrong predictions. To address the above challenges, this paper re-models the above image attribution problem as a submodular subset selection problem, aiming to e"},"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":"2402.09164","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-14T13:30:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7a11705280cc61424b3229f6a7410e38ce80b0f6837e98f1fb204ccc93169534","abstract_canon_sha256":"283befad5810311ff271daaa689550d442614b504848ec180256a69080a9ab14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:49.820007Z","signature_b64":"HJ2FputQs1Tx0pxhs8Zv6xlHX8M7N7T3XmMJuBoU/gGdie/1/9jVP7KQCqEk1+hhv1Kve8OPFHZskO9Ycbs/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8433cda182122bad8e07ce935da1e4104da9fb33001fcea894bb8c5fc10d1a8","last_reissued_at":"2026-07-05T09:03:49.819402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:49.819402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less is More: Fewer Interpretable Region via Submodular Subset Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hua Zhang, Jingzhi Li, Ruoyu Chen, Siyuan Liang, Xiaochun Cao","submitted_at":"2024-02-14T13:30:02Z","abstract_excerpt":"Image attribution algorithms aim to identify important regions that are highly relevant to model decisions. Although existing attribution solutions can effectively assign importance to target elements, they still face the following challenges: 1) existing attribution methods generate inaccurate small regions thus misleading the direction of correct attribution, and 2) the model cannot produce good attribution results for samples with wrong predictions. To address the above challenges, this paper re-models the above image attribution problem as a submodular subset selection problem, aiming to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09164","kind":"arxiv","version":3},"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/2402.09164/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":"2402.09164","created_at":"2026-07-05T09:03:49.819459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09164v3","created_at":"2026-07-05T09:03:49.819459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09164","created_at":"2026-07-05T09:03:49.819459+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBBTZWQYEERL","created_at":"2026-07-05T09:03:49.819459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBBTZWQYEERLVWHA","created_at":"2026-07-05T09:03:49.819459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBBTZWQY","created_at":"2026-07-05T09:03:49.819459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04630","citing_title":"Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE","json":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE.json","graph_json":"https://pith.science/api/pith-number/ZBBTZWQYEERLVWHAPTUTLWQ6IE/graph.json","events_json":"https://pith.science/api/pith-number/ZBBTZWQYEERLVWHAPTUTLWQ6IE/events.json","paper":"https://pith.science/paper/ZBBTZWQY"},"agent_actions":{"view_html":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE","download_json":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE.json","view_paper":"https://pith.science/paper/ZBBTZWQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09164&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBBTZWQYEERLVWHAPTUTLWQ6IE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBBTZWQYEERLVWHAPTUTLWQ6IE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE/action/storage_attestation","attest_author":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE/action/author_attestation","sign_citation":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE/action/citation_signature","submit_replication":"https://pith.science/pith/ZBBTZWQYEERLVWHAPTUTLWQ6IE/action/replication_record"}},"created_at":"2026-07-05T09:03:49.819459+00:00","updated_at":"2026-07-05T09:03:49.819459+00:00"}