{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T3UIITT3MOAP2LRMCDPCGNA2CG","short_pith_number":"pith:T3UIITT3","schema_version":"1.0","canonical_sha256":"9ee8844e7b6380fd2e2c10de23341a1182349575060c3478ee223f3d338a58f8","source":{"kind":"arxiv","id":"2606.22314","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jaesik Choi, Kyowoon Lee, Soyeon Kim","submitted_at":"2026-06-21T03:04:35Z","abstract_excerpt":"Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients along a path from a baseline to the input. However, the choice of the attribution path largely affects the quality of explanations, and existing approaches rely on fixed or hand-crafted paths that often produce noisy or distorted attributions. To address this limitation, we propose Diffusion Integrated Gradients (DiffIG), a novel method that reformulates path generation as a condit"},"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":"2606.22314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T03:04:35Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"76c207e14c4dc6e052a392eb599be54a5d8f9769689541b3870381338dd9a2f0","abstract_canon_sha256":"dbfafd05f5240ea2c7603db087e2c4db4f2090e83d6b40782cb3e2d79d69446f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:34.683881Z","signature_b64":"A+c3IuMrBbCR/GRJS6Gy3BcBstS5TkMUuKQgQgu+NJ5NG1JWVelH/B6xRtYPxG6gwOeIfvJS2qHJ1P/QfqlfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee8844e7b6380fd2e2c10de23341a1182349575060c3478ee223f3d338a58f8","last_reissued_at":"2026-06-23T02:13:34.683453Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:34.683453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jaesik Choi, Kyowoon Lee, Soyeon Kim","submitted_at":"2026-06-21T03:04:35Z","abstract_excerpt":"Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients along a path from a baseline to the input. However, the choice of the attribution path largely affects the quality of explanations, and existing approaches rely on fixed or hand-crafted paths that often produce noisy or distorted attributions. To address this limitation, we propose Diffusion Integrated Gradients (DiffIG), a novel method that reformulates path generation as a condit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22314","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/2606.22314/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":"2606.22314","created_at":"2026-06-23T02:13:34.683520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22314v1","created_at":"2026-06-23T02:13:34.683520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22314","created_at":"2026-06-23T02:13:34.683520+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3UIITT3MOAP","created_at":"2026-06-23T02:13:34.683520+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3UIITT3MOAP2LRM","created_at":"2026-06-23T02:13:34.683520+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3UIITT3","created_at":"2026-06-23T02:13:34.683520+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/T3UIITT3MOAP2LRMCDPCGNA2CG","json":"https://pith.science/pith/T3UIITT3MOAP2LRMCDPCGNA2CG.json","graph_json":"https://pith.science/api/pith-number/T3UIITT3MOAP2LRMCDPCGNA2CG/graph.json","events_json":"https://pith.science/api/pith-number/T3UIITT3MOAP2LRMCDPCGNA2CG/events.json","paper":"https://pith.science/paper/T3UIITT3"},"agent_actions":{"view_html":"https://pith.science/pith/T3UIITT3MOAP2LRMCDPCGNA2CG","download_json":"https://pith.science/pith/T3UIITT3MOAP2LRMCDPCGNA2CG.json","view_paper":"https://pith.science/paper/T3UIITT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22314&json=true","fetch_graph":"https://pith.science/api/pith-number/T3UIITT3MOAP2LRMCDPCGNA2CG/graph.json","fetch_events":"https://pith.science/api/pith-number/T3UIITT3MOAP2LRMCDPCGNA2CG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3UIITT3MOAP2LRMCDPCGNA2CG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3UIITT3MOAP2LRMCDPCGNA2CG/action/storage_attestation","attest_author":"https://pith.science/pith/T3UIITT3MOAP2LRMCDPCGNA2CG/action/author_attestation","sign_citation":"https://pith.science/pith/T3UIITT3MOAP2LRMCDPCGNA2CG/action/citation_signature","submit_replication":"https://pith.science/pith/T3UIITT3MOAP2LRMCDPCGNA2CG/action/replication_record"}},"created_at":"2026-06-23T02:13:34.683520+00:00","updated_at":"2026-06-23T02:13:34.683520+00:00"}