{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TI7KNQNTBUJHJG4W64OMNNT43E","short_pith_number":"pith:TI7KNQNT","canonical_record":{"source":{"id":"2605.14984","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T15:48:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eaf1544c08b63192331a67b36e4a0b06799bff770288f6ab1b982f330ed15341","abstract_canon_sha256":"2d60906ecc86b95c419366811cb472ea3b62ff1979e4558bbdf1840739fd2efe"},"schema_version":"1.0"},"canonical_sha256":"9a3ea6c1b30d12749b96f71cc6b67cd9100f9a23fcf92c836bd1248e85203332","source":{"kind":"arxiv","id":"2605.14984","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14984","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14984v1","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14984","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"TI7KNQNTBUJH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TI7KNQNTBUJHJG4W","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TI7KNQNT","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TI7KNQNTBUJHJG4W64OMNNT43E","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14984","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T15:48:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eaf1544c08b63192331a67b36e4a0b06799bff770288f6ab1b982f330ed15341","abstract_canon_sha256":"2d60906ecc86b95c419366811cb472ea3b62ff1979e4558bbdf1840739fd2efe"},"schema_version":"1.0"},"canonical_sha256":"9a3ea6c1b30d12749b96f71cc6b67cd9100f9a23fcf92c836bd1248e85203332","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:55.085284Z","signature_b64":"apx269M/HHI/umE/Z+9Uzr5JaZewMTNuVVAc+7n+YmokxodzKEF+MjKaDvhxV+oSopeFBLe4Zk8gAb+n1vBPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a3ea6c1b30d12749b96f71cc6b67cd9100f9a23fcf92c836bd1248e85203332","last_reissued_at":"2026-05-17T23:38:55.084592Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:55.084592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14984","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afNAZLdJtvE1Iynl2u0V30QMP8EjYQDnQCizELUDqm5jiNigV9r7SAFJRcBCgE9CaXPRVAxq+PS0UMg8DkW1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:14:34.982728Z"},"content_sha256":"071904e11304787fe5973450347f0581556904cc03efd6c6ce974a8d131b224d","schema_version":"1.0","event_id":"sha256:071904e11304787fe5973450347f0581556904cc03efd6c6ce974a8d131b224d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TI7KNQNTBUJHJG4W64OMNNT43E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A geometry-first training strategy generates accurate street-level 3D scenes directly from single satellite images.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Tan, Changkun Liu, Gui-Song Xia, Hang Zhang, Ming Qian, Shuailei Ma, Wen Wang, Zeran Ke, Zimin Xia","submitted_at":"2026-05-14T15:48:15Z","abstract_excerpt":"Generating a street-level 3D scene from a single satellite image is a crucial yet challenging task. Current methods present a stark trade-off: geometry-colorization models achieve high geometric fidelity but are typically building-focused and lack semantic diversity. In contrast, proxy-based models use feed-forward image-to-3D frameworks to generate holistic scenes by jointly learning geometry and texture, a process that yields rich content but coarse and unstable geometry. We attribute these geometric failures to the extreme viewpoint gap and sparse, inconsistent supervision inherent in satel"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our geometry-first methodology yields a dramatic leap in both 3D accuracy and photorealism, improving geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 on the VIGOR-OOD benchmark with DSM data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The extreme viewpoint gap and sparse inconsistent supervision in satellite-to-street data can be effectively countered by integrating novel geometric constraints with a perspective-view training strategy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A geometry-first training strategy generates accurate street-level 3D scenes directly from single satellite images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a37ee0a008233d939339be9abaff5e0be787c9803e1cae31e3c7e063262e7edf"},"source":{"id":"2605.14984","kind":"arxiv","version":1},"verdict":{"id":"5e60c650-1769-49c0-a5db-122bedfd475f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:11:15.943077Z","strongest_claim":"Our geometry-first methodology yields a dramatic leap in both 3D accuracy and photorealism, improving geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 on the VIGOR-OOD benchmark with DSM data.","one_line_summary":"Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The extreme viewpoint gap and sparse inconsistent supervision in satellite-to-street data can be effectively countered by integrating novel geometric constraints with a perspective-view training strategy.","pith_extraction_headline":"A geometry-first training strategy generates accurate street-level 3D scenes directly from single satellite images."},"references":{"count":119,"sample":[{"doi":"","year":null,"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Deep learning , author=. 2016 , publisher=","work_id":"cf0899e0-53ee-4591-aae4-f38fa5ac12ad","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Chan and Connor Z","work_id":"fc7aad7e-d553-4af3-b43a-f9ac64a458a4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"3D-aware Conditional Image Synthesis , author=","work_id":"67ba7d0b-971b-4a34-aba9-2f1744b432a9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":119,"snapshot_sha256":"1f188f288ffea0991fd2f76d8a0bccab8608dc04dabc46ef81af6c536417d321","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"939e7cb362f357c501483f4a3c657397ebef0e0192272728a57c4295415f0968"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5e60c650-1769-49c0-a5db-122bedfd475f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v60emKT5OzOfvsOjUe/SjeZS0qhZcTvmIJwUxqc2t3g07CqA71egNuykLLydww43CPVuSWRQGB6nXvM1NJP0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:14:34.983248Z"},"content_sha256":"d140a00d1e231558dfc6930528324f7e2500c1e1fa501a807003ee7373b0d046","schema_version":"1.0","event_id":"sha256:d140a00d1e231558dfc6930528324f7e2500c1e1fa501a807003ee7373b0d046"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TI7KNQNTBUJHJG4W64OMNNT43E/bundle.json","state_url":"https://pith.science/pith/TI7KNQNTBUJHJG4W64OMNNT43E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TI7KNQNTBUJHJG4W64OMNNT43E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T14:14:34Z","links":{"resolver":"https://pith.science/pith/TI7KNQNTBUJHJG4W64OMNNT43E","bundle":"https://pith.science/pith/TI7KNQNTBUJHJG4W64OMNNT43E/bundle.json","state":"https://pith.science/pith/TI7KNQNTBUJHJG4W64OMNNT43E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TI7KNQNTBUJHJG4W64OMNNT43E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TI7KNQNTBUJHJG4W64OMNNT43E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2d60906ecc86b95c419366811cb472ea3b62ff1979e4558bbdf1840739fd2efe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T15:48:15Z","title_canon_sha256":"eaf1544c08b63192331a67b36e4a0b06799bff770288f6ab1b982f330ed15341"},"schema_version":"1.0","source":{"id":"2605.14984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14984","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14984v1","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14984","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"TI7KNQNTBUJH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TI7KNQNTBUJHJG4W","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TI7KNQNT","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d140a00d1e231558dfc6930528324f7e2500c1e1fa501a807003ee7373b0d046","target":"graph","created_at":"2026-05-17T23:38:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our geometry-first methodology yields a dramatic leap in both 3D accuracy and photorealism, improving geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 on the VIGOR-OOD benchmark with DSM data."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The extreme viewpoint gap and sparse inconsistent supervision in satellite-to-street data can be effectively countered by integrating novel geometric constraints with a perspective-view training strategy."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A geometry-first training strategy generates accurate street-level 3D scenes directly from single satellite images."}],"snapshot_sha256":"a37ee0a008233d939339be9abaff5e0be787c9803e1cae31e3c7e063262e7edf"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"939e7cb362f357c501483f4a3c657397ebef0e0192272728a57c4295415f0968"},"paper":{"abstract_excerpt":"Generating a street-level 3D scene from a single satellite image is a crucial yet challenging task. Current methods present a stark trade-off: geometry-colorization models achieve high geometric fidelity but are typically building-focused and lack semantic diversity. In contrast, proxy-based models use feed-forward image-to-3D frameworks to generate holistic scenes by jointly learning geometry and texture, a process that yields rich content but coarse and unstable geometry. We attribute these geometric failures to the extreme viewpoint gap and sparse, inconsistent supervision inherent in satel","authors_text":"Bin Tan, Changkun Liu, Gui-Song Xia, Hang Zhang, Ming Qian, Shuailei Ma, Wen Wang, Zeran Ke, Zimin Xia","cross_cats":["cs.AI"],"headline":"A geometry-first training strategy generates accurate street-level 3D scenes directly from single satellite images.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T15:48:15Z","title":"Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image"},"references":{"count":119,"internal_anchors":5,"resolved_work":119,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Deep learning , author=. 2016 , publisher=","work_id":"cf0899e0-53ee-4591-aae4-f38fa5ac12ad","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Chan and Connor Z","work_id":"fc7aad7e-d553-4af3-b43a-f9ac64a458a4","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"3D-aware Conditional Image Synthesis , author=","work_id":"67ba7d0b-971b-4a34-aba9-2f1744b432a9","year":null}],"snapshot_sha256":"1f188f288ffea0991fd2f76d8a0bccab8608dc04dabc46ef81af6c536417d321"},"source":{"id":"2605.14984","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:11:15.943077Z","id":"5e60c650-1769-49c0-a5db-122bedfd475f","model_set":{"reader":"grok-4.3"},"one_line_summary":"Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A geometry-first training strategy generates accurate street-level 3D scenes directly from single satellite images.","strongest_claim":"Our geometry-first methodology yields a dramatic leap in both 3D accuracy and photorealism, improving geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 on the VIGOR-OOD benchmark with DSM data.","weakest_assumption":"The extreme viewpoint gap and sparse inconsistent supervision in satellite-to-street data can be effectively countered by integrating novel geometric constraints with a perspective-view training strategy."}},"verdict_id":"5e60c650-1769-49c0-a5db-122bedfd475f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:071904e11304787fe5973450347f0581556904cc03efd6c6ce974a8d131b224d","target":"record","created_at":"2026-05-17T23:38:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2d60906ecc86b95c419366811cb472ea3b62ff1979e4558bbdf1840739fd2efe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T15:48:15Z","title_canon_sha256":"eaf1544c08b63192331a67b36e4a0b06799bff770288f6ab1b982f330ed15341"},"schema_version":"1.0","source":{"id":"2605.14984","kind":"arxiv","version":1}},"canonical_sha256":"9a3ea6c1b30d12749b96f71cc6b67cd9100f9a23fcf92c836bd1248e85203332","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a3ea6c1b30d12749b96f71cc6b67cd9100f9a23fcf92c836bd1248e85203332","first_computed_at":"2026-05-17T23:38:55.084592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:55.084592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"apx269M/HHI/umE/Z+9Uzr5JaZewMTNuVVAc+7n+YmokxodzKEF+MjKaDvhxV+oSopeFBLe4Zk8gAb+n1vBPDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:55.085284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:071904e11304787fe5973450347f0581556904cc03efd6c6ce974a8d131b224d","sha256:d140a00d1e231558dfc6930528324f7e2500c1e1fa501a807003ee7373b0d046"],"state_sha256":"b7297fe38a79e553d1caa1e8fe67ca050ea022f7b654fdd9b4548b66e664529f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"noSGzVfTcMjVJ8QXf35iuHDP0c62/c1oeN3gn9jLbdLRY6+7rQqLs+J0RDVgcq1Z0rHcoeEfOxMTuExF4pBxCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T14:14:34.987024Z","bundle_sha256":"8950e9999ced75ee12d24d3798a6ee25714d061c1dfaeac62f92300ba36c034f"}}