{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MG7TBZIIKBQF25Y4FQOMOVCNXI","short_pith_number":"pith:MG7TBZII","schema_version":"1.0","canonical_sha256":"61bf30e50850605d771c2c1cc7544dba28a885d2375963dddb5a054d3dedd50b","source":{"kind":"arxiv","id":"2409.01491","version":2},"attestation_state":"computed","paper":{"title":"EarthGen: Generating the World from Top-Down Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Albert Xiao, Albert Zhai, Ansh Sharma, Praneet Rathi, Rohit Kundu, Shenlong Wang, Yuan Shen","submitted_at":"2024-09-02T23:17:56Z","abstract_excerpt":"In this work, we present a novel method for extensive multi-scale generative terrain modeling. At the core of our model is a cascade of superresolution diffusion models that can be combined to produce consistent images across multiple resolutions. Pairing this concept with a tiled generation method yields a scalable system that can generate thousands of square kilometers of realistic Earth surfaces at high resolution. We evaluate our method on a dataset collected from Bing Maps and show that it outperforms super-resolution baselines on the extreme super-resolution task of 1024x zoom. We also d"},"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":"2409.01491","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-02T23:17:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dfb965248efad07225b3d5cde50ccdec001fe44c5c90c74a1f08b14f725b6cc9","abstract_canon_sha256":"fac8d831dc285f6cb7781f9f73a0a256dca99d69f0850711a88e833a491cf58f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:55.204638Z","signature_b64":"EZWhFoJ36J7qQrPP/RNPDzi2mZ90ngSYtBvDgDH+1uhgt18fqoPsZT2Zrf0xWRe246J3IiCcCkJYF1FoNwe3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61bf30e50850605d771c2c1cc7544dba28a885d2375963dddb5a054d3dedd50b","last_reissued_at":"2026-07-05T09:05:55.204124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:55.204124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EarthGen: Generating the World from Top-Down Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Albert Xiao, Albert Zhai, Ansh Sharma, Praneet Rathi, Rohit Kundu, Shenlong Wang, Yuan Shen","submitted_at":"2024-09-02T23:17:56Z","abstract_excerpt":"In this work, we present a novel method for extensive multi-scale generative terrain modeling. At the core of our model is a cascade of superresolution diffusion models that can be combined to produce consistent images across multiple resolutions. Pairing this concept with a tiled generation method yields a scalable system that can generate thousands of square kilometers of realistic Earth surfaces at high resolution. We evaluate our method on a dataset collected from Bing Maps and show that it outperforms super-resolution baselines on the extreme super-resolution task of 1024x zoom. We also d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01491","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/2409.01491/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":"2409.01491","created_at":"2026-07-05T09:05:55.204184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01491v2","created_at":"2026-07-05T09:05:55.204184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01491","created_at":"2026-07-05T09:05:55.204184+00:00"},{"alias_kind":"pith_short_12","alias_value":"MG7TBZIIKBQF","created_at":"2026-07-05T09:05:55.204184+00:00"},{"alias_kind":"pith_short_16","alias_value":"MG7TBZIIKBQF25Y4","created_at":"2026-07-05T09:05:55.204184+00:00"},{"alias_kind":"pith_short_8","alias_value":"MG7TBZII","created_at":"2026-07-05T09:05:55.204184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.08309","citing_title":"InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI","json":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI.json","graph_json":"https://pith.science/api/pith-number/MG7TBZIIKBQF25Y4FQOMOVCNXI/graph.json","events_json":"https://pith.science/api/pith-number/MG7TBZIIKBQF25Y4FQOMOVCNXI/events.json","paper":"https://pith.science/paper/MG7TBZII"},"agent_actions":{"view_html":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI","download_json":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI.json","view_paper":"https://pith.science/paper/MG7TBZII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01491&json=true","fetch_graph":"https://pith.science/api/pith-number/MG7TBZIIKBQF25Y4FQOMOVCNXI/graph.json","fetch_events":"https://pith.science/api/pith-number/MG7TBZIIKBQF25Y4FQOMOVCNXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI/action/storage_attestation","attest_author":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI/action/author_attestation","sign_citation":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI/action/citation_signature","submit_replication":"https://pith.science/pith/MG7TBZIIKBQF25Y4FQOMOVCNXI/action/replication_record"}},"created_at":"2026-07-05T09:05:55.204184+00:00","updated_at":"2026-07-05T09:05:55.204184+00:00"}