{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SZN4F45Q4EM4AB2RXTXNJZJS66","short_pith_number":"pith:SZN4F45Q","schema_version":"1.0","canonical_sha256":"965bc2f3b0e119c00751bceed4e532f7a3571ad26078e9c9d93accca78d82ddc","source":{"kind":"arxiv","id":"2603.01140","version":2},"attestation_state":"computed","paper":{"title":"Teacher-Guided Causal Interventions for Image Denoising: Orthogonal Content-Noise Disentanglement in Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dianjie Lu, Guijuan Zhang, Kuai Jiang, Zhaoyan Ding, Zhuoran Zheng","submitted_at":"2026-03-01T15:04:37Z","abstract_excerpt":"Conventional image denoising models often inadvertently learn spurious correlations between environmental factors and noise patterns. Moreover, due to high-frequency ambiguity, they struggle to reliably distinguish subtle textures from stochastic noise, resulting in over-removed details or residual noise artifacts. We therefore revisit denoising via causal intervention, arguing that purely correlational fitting entangles intrinsic content with extrinsic noise, which directly degrades robustness under distribution shifts. Motivated by this, we propose the Teacher-Guided Causal Disentanglement N"},"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":"2603.01140","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-01T15:04:37Z","cross_cats_sorted":[],"title_canon_sha256":"09ec63d528f0f0429e3ec26e2d8018f4a761a86181dfadd447936fd14a934d32","abstract_canon_sha256":"602dc8adbe69791f04ac041a20a5c8eaba19ed44bc485d1c5ef8366cac9979cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:46.501740Z","signature_b64":"PbjN/bX1xb19y2tf19W4sKGkxfLJYv9elZbUIrBwR2EMHfCyswAWgcu+dl7jvhFhnisbD4WOq8sXZc/sEVkJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"965bc2f3b0e119c00751bceed4e532f7a3571ad26078e9c9d93accca78d82ddc","last_reissued_at":"2026-07-17T01:21:46.500883Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:46.500883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teacher-Guided Causal Interventions for Image Denoising: Orthogonal Content-Noise Disentanglement in Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dianjie Lu, Guijuan Zhang, Kuai Jiang, Zhaoyan Ding, Zhuoran Zheng","submitted_at":"2026-03-01T15:04:37Z","abstract_excerpt":"Conventional image denoising models often inadvertently learn spurious correlations between environmental factors and noise patterns. Moreover, due to high-frequency ambiguity, they struggle to reliably distinguish subtle textures from stochastic noise, resulting in over-removed details or residual noise artifacts. We therefore revisit denoising via causal intervention, arguing that purely correlational fitting entangles intrinsic content with extrinsic noise, which directly degrades robustness under distribution shifts. Motivated by this, we propose the Teacher-Guided Causal Disentanglement N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.01140","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/2603.01140/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":"2603.01140","created_at":"2026-07-17T01:21:46.501282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.01140v2","created_at":"2026-07-17T01:21:46.501282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.01140","created_at":"2026-07-17T01:21:46.501282+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZN4F45Q4EM4","created_at":"2026-07-17T01:21:46.501282+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZN4F45Q4EM4AB2R","created_at":"2026-07-17T01:21:46.501282+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZN4F45Q","created_at":"2026-07-17T01:21:46.501282+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/SZN4F45Q4EM4AB2RXTXNJZJS66","json":"https://pith.science/pith/SZN4F45Q4EM4AB2RXTXNJZJS66.json","graph_json":"https://pith.science/api/pith-number/SZN4F45Q4EM4AB2RXTXNJZJS66/graph.json","events_json":"https://pith.science/api/pith-number/SZN4F45Q4EM4AB2RXTXNJZJS66/events.json","paper":"https://pith.science/paper/SZN4F45Q"},"agent_actions":{"view_html":"https://pith.science/pith/SZN4F45Q4EM4AB2RXTXNJZJS66","download_json":"https://pith.science/pith/SZN4F45Q4EM4AB2RXTXNJZJS66.json","view_paper":"https://pith.science/paper/SZN4F45Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.01140&json=true","fetch_graph":"https://pith.science/api/pith-number/SZN4F45Q4EM4AB2RXTXNJZJS66/graph.json","fetch_events":"https://pith.science/api/pith-number/SZN4F45Q4EM4AB2RXTXNJZJS66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZN4F45Q4EM4AB2RXTXNJZJS66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZN4F45Q4EM4AB2RXTXNJZJS66/action/storage_attestation","attest_author":"https://pith.science/pith/SZN4F45Q4EM4AB2RXTXNJZJS66/action/author_attestation","sign_citation":"https://pith.science/pith/SZN4F45Q4EM4AB2RXTXNJZJS66/action/citation_signature","submit_replication":"https://pith.science/pith/SZN4F45Q4EM4AB2RXTXNJZJS66/action/replication_record"}},"created_at":"2026-07-17T01:21:46.501282+00:00","updated_at":"2026-07-17T01:21:46.501282+00:00"}