{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IAEV7UDMX2YJXEV6WVWZPT5BTC","short_pith_number":"pith:IAEV7UDM","schema_version":"1.0","canonical_sha256":"40095fd06cbeb09b92beb56d97cfa19883e66f31c43424fa793543691694cdb5","source":{"kind":"arxiv","id":"2603.25129","version":2},"attestation_state":"computed","paper":{"title":"AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jaeho Moon, Minh-Quan Viet Bui, Munchurl Kim","submitted_at":"2026-03-26T07:52:33Z","abstract_excerpt":"While 3D Vision Foundation Models (3DVFMs) have demonstrated remarkable zero-shot capabilities in visual geometry estimation, their direct application to generalizable novel view synthesis (NVS) remains challenging.\n  In this paper, we propose AirSplat, a novel training framework that effectively adapts the robust geometric priors of 3DVFMs into high-fidelity, pose-free NVS. Our approach introduces two key technical contributions:\n  (1) Self-Consistent Pose Alignment (SCPA), a training-time feedback loop that ensures pixel-aligned supervision to resolve pose-geometry discrepancy; and\n  (2) Rat"},"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":"2603.25129","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-26T07:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"439245903881dea7c00f36740bab87a3050a72f442b7fdd188559c937bd99f4a","abstract_canon_sha256":"06a32cd6d188d8eab30405ae0110bb9fa4da4a7557e52d274ef8fd1c53a87c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:52:36.207546Z","signature_b64":"flYeS2gLbDkFSfu+boRMKYh5pR432qUoOIRGu1sXfWHV4u99jURARwWwIx49ufww2Dwld83v4+5ea9339uzTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40095fd06cbeb09b92beb56d97cfa19883e66f31c43424fa793543691694cdb5","last_reissued_at":"2026-08-04T01:52:36.205805Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:52:36.205805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jaeho Moon, Minh-Quan Viet Bui, Munchurl Kim","submitted_at":"2026-03-26T07:52:33Z","abstract_excerpt":"While 3D Vision Foundation Models (3DVFMs) have demonstrated remarkable zero-shot capabilities in visual geometry estimation, their direct application to generalizable novel view synthesis (NVS) remains challenging.\n  In this paper, we propose AirSplat, a novel training framework that effectively adapts the robust geometric priors of 3DVFMs into high-fidelity, pose-free NVS. Our approach introduces two key technical contributions:\n  (1) Self-Consistent Pose Alignment (SCPA), a training-time feedback loop that ensures pixel-aligned supervision to resolve pose-geometry discrepancy; and\n  (2) Rat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25129","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/2603.25129/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":"2603.25129","created_at":"2026-08-04T01:52:36.207076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.25129v2","created_at":"2026-08-04T01:52:36.207076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25129","created_at":"2026-08-04T01:52:36.207076+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAEV7UDMX2YJ","created_at":"2026-08-04T01:52:36.207076+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAEV7UDMX2YJXEV6","created_at":"2026-08-04T01:52:36.207076+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAEV7UDM","created_at":"2026-08-04T01:52:36.207076+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/IAEV7UDMX2YJXEV6WVWZPT5BTC","json":"https://pith.science/pith/IAEV7UDMX2YJXEV6WVWZPT5BTC.json","graph_json":"https://pith.science/api/pith-number/IAEV7UDMX2YJXEV6WVWZPT5BTC/graph.json","events_json":"https://pith.science/api/pith-number/IAEV7UDMX2YJXEV6WVWZPT5BTC/events.json","paper":"https://pith.science/paper/IAEV7UDM"},"agent_actions":{"view_html":"https://pith.science/pith/IAEV7UDMX2YJXEV6WVWZPT5BTC","download_json":"https://pith.science/pith/IAEV7UDMX2YJXEV6WVWZPT5BTC.json","view_paper":"https://pith.science/paper/IAEV7UDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.25129&json=true","fetch_graph":"https://pith.science/api/pith-number/IAEV7UDMX2YJXEV6WVWZPT5BTC/graph.json","fetch_events":"https://pith.science/api/pith-number/IAEV7UDMX2YJXEV6WVWZPT5BTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAEV7UDMX2YJXEV6WVWZPT5BTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAEV7UDMX2YJXEV6WVWZPT5BTC/action/storage_attestation","attest_author":"https://pith.science/pith/IAEV7UDMX2YJXEV6WVWZPT5BTC/action/author_attestation","sign_citation":"https://pith.science/pith/IAEV7UDMX2YJXEV6WVWZPT5BTC/action/citation_signature","submit_replication":"https://pith.science/pith/IAEV7UDMX2YJXEV6WVWZPT5BTC/action/replication_record"}},"created_at":"2026-08-04T01:52:36.207076+00:00","updated_at":"2026-08-04T01:52:36.207076+00:00"}