{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2Q3UJD7O3LXNFFYSDVTM6Y4CR7","short_pith_number":"pith:2Q3UJD7O","schema_version":"1.0","canonical_sha256":"d437448feedaeed297121d66cf63828ffec3a95c2f11cd78f2ff86a787f63f04","source":{"kind":"arxiv","id":"2311.17833","version":3},"attestation_state":"computed","paper":{"title":"DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Matthias Hein, Maximilian Augustin, Yannic Neuhaus","submitted_at":"2023-11-29T17:35:29Z","abstract_excerpt":"While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for safety-critical tasks the black-box nature of their decisions is problematic, and explanations or at least methods which make decisions plausible are needed urgently. In this paper, we address these problems by generating images that optimize a classifier-derived objective using a framework for guided image generation. We analyze the decisions of image classifi"},"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":"2311.17833","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T17:35:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ec7c25041aca6a67dd8b838f6069372a131adc0ef5a3994cf0fd92a3b9e2c7f1","abstract_canon_sha256":"cd5a604594a23e94b6abbd63568b8155da11a91d3590109a7b093a24b3f94835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:07.785948Z","signature_b64":"btXC81c44lNaeGl0G122ieg+JAjPiV2jh3VLvadrHSwrO9W5+jr523+nLb2jNs+aQvFlISw86RhNKmhWjB47Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d437448feedaeed297121d66cf63828ffec3a95c2f11cd78f2ff86a787f63f04","last_reissued_at":"2026-07-05T08:43:07.785469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:07.785469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Matthias Hein, Maximilian Augustin, Yannic Neuhaus","submitted_at":"2023-11-29T17:35:29Z","abstract_excerpt":"While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for safety-critical tasks the black-box nature of their decisions is problematic, and explanations or at least methods which make decisions plausible are needed urgently. In this paper, we address these problems by generating images that optimize a classifier-derived objective using a framework for guided image generation. We analyze the decisions of image classifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17833","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/2311.17833/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":"2311.17833","created_at":"2026-07-05T08:43:07.785535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17833v3","created_at":"2026-07-05T08:43:07.785535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17833","created_at":"2026-07-05T08:43:07.785535+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Q3UJD7O3LXN","created_at":"2026-07-05T08:43:07.785535+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Q3UJD7O3LXNFFYS","created_at":"2026-07-05T08:43:07.785535+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Q3UJD7O","created_at":"2026-07-05T08:43:07.785535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10877","citing_title":"XtrAIn: Training-Guided Occlusion for Feature Attribution","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7","json":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7.json","graph_json":"https://pith.science/api/pith-number/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/graph.json","events_json":"https://pith.science/api/pith-number/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/events.json","paper":"https://pith.science/paper/2Q3UJD7O"},"agent_actions":{"view_html":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7","download_json":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7.json","view_paper":"https://pith.science/paper/2Q3UJD7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17833&json=true","fetch_graph":"https://pith.science/api/pith-number/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/graph.json","fetch_events":"https://pith.science/api/pith-number/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/action/storage_attestation","attest_author":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/action/author_attestation","sign_citation":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/action/citation_signature","submit_replication":"https://pith.science/pith/2Q3UJD7O3LXNFFYSDVTM6Y4CR7/action/replication_record"}},"created_at":"2026-07-05T08:43:07.785535+00:00","updated_at":"2026-07-05T08:43:07.785535+00:00"}