{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BXBLOSNP42WWQW6FVS5F3VH5GT","short_pith_number":"pith:BXBLOSNP","schema_version":"1.0","canonical_sha256":"0dc2b749afe6ad685bc5acba5dd4fd34c9a58919987ae2a533fd0d1cbd418542","source":{"kind":"arxiv","id":"2602.22867","version":2},"attestation_state":"computed","paper":{"title":"SO3UFormer: Learning Intrinsic Spherical Features for Rotation-Robust Panoramic Dense Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Fan, Qinfeng Zhu, Yunxi Jiang","submitted_at":"2026-02-26T11:07:51Z","abstract_excerpt":"Panoramic dense-prediction models, spanning semantic segmentation and depth estimation, are typically trained under a strict gravity-aligned assumption. Real-world captures, however, routinely violate it: handheld devices jitter and aerial platforms change attitude, so the camera is rarely upright. Under such 3D reorientation, standard spherical Transformers overfit global latitude cues and collapse. We introduce SO3UFormer, an architecture that learns intrinsic spherical features largely decoupled from the underlying coordinate frame, through three geometric components: (1) removing absolute "},"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":"2602.22867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T11:07:51Z","cross_cats_sorted":[],"title_canon_sha256":"0f9aedb4649f72f90da2c73b78f3d2ff3b35f62aa597e2cb5290ea3e06d95c18","abstract_canon_sha256":"1a89a72c064ead5b58728220df7e24eb5621e35a8297e46441653482271f4434"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:55.124585Z","signature_b64":"IwWuwSzgQMMkD5G8EVjcR8UWjR+/14nYdm8sfK3WolUgCBjZNiMZGv0/0V+koewBxWKkZf2Vqex/SoHHoAo/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dc2b749afe6ad685bc5acba5dd4fd34c9a58919987ae2a533fd0d1cbd418542","last_reissued_at":"2026-07-14T01:20:55.123625Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:55.123625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SO3UFormer: Learning Intrinsic Spherical Features for Rotation-Robust Panoramic Dense Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Fan, Qinfeng Zhu, Yunxi Jiang","submitted_at":"2026-02-26T11:07:51Z","abstract_excerpt":"Panoramic dense-prediction models, spanning semantic segmentation and depth estimation, are typically trained under a strict gravity-aligned assumption. Real-world captures, however, routinely violate it: handheld devices jitter and aerial platforms change attitude, so the camera is rarely upright. Under such 3D reorientation, standard spherical Transformers overfit global latitude cues and collapse. We introduce SO3UFormer, an architecture that learns intrinsic spherical features largely decoupled from the underlying coordinate frame, through three geometric components: (1) removing absolute "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22867","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/2602.22867/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":"2602.22867","created_at":"2026-07-14T01:20:55.124044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22867v2","created_at":"2026-07-14T01:20:55.124044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22867","created_at":"2026-07-14T01:20:55.124044+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXBLOSNP42WW","created_at":"2026-07-14T01:20:55.124044+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXBLOSNP42WWQW6F","created_at":"2026-07-14T01:20:55.124044+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXBLOSNP","created_at":"2026-07-14T01:20:55.124044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.27745","citing_title":"Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling","ref_index":143,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT","json":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT.json","graph_json":"https://pith.science/api/pith-number/BXBLOSNP42WWQW6FVS5F3VH5GT/graph.json","events_json":"https://pith.science/api/pith-number/BXBLOSNP42WWQW6FVS5F3VH5GT/events.json","paper":"https://pith.science/paper/BXBLOSNP"},"agent_actions":{"view_html":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT","download_json":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT.json","view_paper":"https://pith.science/paper/BXBLOSNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22867&json=true","fetch_graph":"https://pith.science/api/pith-number/BXBLOSNP42WWQW6FVS5F3VH5GT/graph.json","fetch_events":"https://pith.science/api/pith-number/BXBLOSNP42WWQW6FVS5F3VH5GT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT/action/storage_attestation","attest_author":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT/action/author_attestation","sign_citation":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT/action/citation_signature","submit_replication":"https://pith.science/pith/BXBLOSNP42WWQW6FVS5F3VH5GT/action/replication_record"}},"created_at":"2026-07-14T01:20:55.124044+00:00","updated_at":"2026-07-14T01:20:55.124044+00:00"}