{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JHQYJR64ZSYE3T7RQ466H432PC","short_pith_number":"pith:JHQYJR64","schema_version":"1.0","canonical_sha256":"49e184c7dcccb04dcff1873de3f37a7886edb91a53b10b9972e50335cd041414","source":{"kind":"arxiv","id":"2506.18520","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Image Restoration Transformer via Adaptive Translation Equivariance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangzhou He, Jiakui Hu, Lujia Jin, Yanye Lu, Zhengjian Yao","submitted_at":"2025-06-23T11:23:04Z","abstract_excerpt":"Translation equivariance is a fundamental inductive bias in image restoration, ensuring that translated inputs produce translated outputs. Attention mechanisms in modern restoration transformers undermine this property, adversely impacting both training convergence and generalization. To alleviate this issue, we propose two key strategies for incorporating translation equivariance: slide indexing and component stacking. Slide indexing maintains operator responses at fixed positions, with sliding window attention being a notable example, while component stacking enables the arrangement of trans"},"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":"2506.18520","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T11:23:04Z","cross_cats_sorted":[],"title_canon_sha256":"a505bdfe1f74f079d961033de9bf2dbdc0a43658c1406d681a1b5e67603e9331","abstract_canon_sha256":"527c1fcc01c9236dbf31f45b7fe889e2cec29612354909ddfbe7ed1253b946cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:51.369958Z","signature_b64":"DgGIRvxz92iNXkR4Ilewrr29sfFZMOp/hfwGQCrTZoZsI3GZBaZOhJOcDsq938rm7dQz2Y0mEKzMjQmKs6k2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49e184c7dcccb04dcff1873de3f37a7886edb91a53b10b9972e50335cd041414","last_reissued_at":"2026-07-05T11:25:51.369444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:51.369444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Image Restoration Transformer via Adaptive Translation Equivariance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangzhou He, Jiakui Hu, Lujia Jin, Yanye Lu, Zhengjian Yao","submitted_at":"2025-06-23T11:23:04Z","abstract_excerpt":"Translation equivariance is a fundamental inductive bias in image restoration, ensuring that translated inputs produce translated outputs. Attention mechanisms in modern restoration transformers undermine this property, adversely impacting both training convergence and generalization. To alleviate this issue, we propose two key strategies for incorporating translation equivariance: slide indexing and component stacking. Slide indexing maintains operator responses at fixed positions, with sliding window attention being a notable example, while component stacking enables the arrangement of trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18520","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/2506.18520/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":"2506.18520","created_at":"2026-07-05T11:25:51.369525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18520v1","created_at":"2026-07-05T11:25:51.369525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18520","created_at":"2026-07-05T11:25:51.369525+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHQYJR64ZSYE","created_at":"2026-07-05T11:25:51.369525+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHQYJR64ZSYE3T7R","created_at":"2026-07-05T11:25:51.369525+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHQYJR64","created_at":"2026-07-05T11:25:51.369525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11444","citing_title":"Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11444","citing_title":"Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC","json":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC.json","graph_json":"https://pith.science/api/pith-number/JHQYJR64ZSYE3T7RQ466H432PC/graph.json","events_json":"https://pith.science/api/pith-number/JHQYJR64ZSYE3T7RQ466H432PC/events.json","paper":"https://pith.science/paper/JHQYJR64"},"agent_actions":{"view_html":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC","download_json":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC.json","view_paper":"https://pith.science/paper/JHQYJR64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18520&json=true","fetch_graph":"https://pith.science/api/pith-number/JHQYJR64ZSYE3T7RQ466H432PC/graph.json","fetch_events":"https://pith.science/api/pith-number/JHQYJR64ZSYE3T7RQ466H432PC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC/action/storage_attestation","attest_author":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC/action/author_attestation","sign_citation":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC/action/citation_signature","submit_replication":"https://pith.science/pith/JHQYJR64ZSYE3T7RQ466H432PC/action/replication_record"}},"created_at":"2026-07-05T11:25:51.369525+00:00","updated_at":"2026-07-05T11:25:51.369525+00:00"}