{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:INUO5E76B6MIIG7KF3VIAAFQLA","short_pith_number":"pith:INUO5E76","schema_version":"1.0","canonical_sha256":"4368ee93fe0f98841bea2eea8000b0580117809262286d72edc985150a952671","source":{"kind":"arxiv","id":"2605.18599","version":1},"attestation_state":"computed","paper":{"title":"Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junchi Yan, Shaofeng Zhang, Xiaosong Jia, Yihang Sun, Yihang Wu, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2026-05-18T16:09:52Z","abstract_excerpt":"Transformer-based models have advanced feedforward novel view synthesis (NVS). Current architectures such as GS-LRM and LVSM mix semantic information (e.g., RGB) and spatial information (e.g., Pl\\\"ucker rays) into a shared feature space. Since Pl\\\"ucker rays naturally carry lattice-like spatial structure, these designs can make the spatial bias interfere with appearance representation and degrade rendering fidelity. To this end, we propose to decouple the representation of feedforward NVS transformers into separate semantic and spatial tokens. The decoupled design keeps semantic and spatial in"},"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":"2605.18599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"d4beff5328a9504f2984876db5184ce31370f37f1480cfd0afceb19a035b3ff6","abstract_canon_sha256":"51cc49696739d4ec3e1362fab9c4b56340b2896f3eefa1cf47fc641403eae24b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:10.175637Z","signature_b64":"FPa3w5BTv7+Jz5jPNhBUCbuvWvvuASoIRzT7sxNbrxJNlx8Xbs1NI2nOY5m1fuMZrSZtE/wXPYwfpUH4neubCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4368ee93fe0f98841bea2eea8000b0580117809262286d72edc985150a952671","last_reissued_at":"2026-05-20T00:06:10.174723Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:10.174723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junchi Yan, Shaofeng Zhang, Xiaosong Jia, Yihang Sun, Yihang Wu, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2026-05-18T16:09:52Z","abstract_excerpt":"Transformer-based models have advanced feedforward novel view synthesis (NVS). Current architectures such as GS-LRM and LVSM mix semantic information (e.g., RGB) and spatial information (e.g., Pl\\\"ucker rays) into a shared feature space. Since Pl\\\"ucker rays naturally carry lattice-like spatial structure, these designs can make the spatial bias interfere with appearance representation and degrade rendering fidelity. To this end, we propose to decouple the representation of feedforward NVS transformers into separate semantic and spatial tokens. The decoupled design keeps semantic and spatial in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18599","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/2605.18599/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.259005Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"14a9b639fda5edc430b38714dcb674116f6d5fbc4a66f9741c67472c3b43ab92"},"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":"2605.18599","created_at":"2026-05-20T00:06:10.174845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18599v1","created_at":"2026-05-20T00:06:10.174845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18599","created_at":"2026-05-20T00:06:10.174845+00:00"},{"alias_kind":"pith_short_12","alias_value":"INUO5E76B6MI","created_at":"2026-05-20T00:06:10.174845+00:00"},{"alias_kind":"pith_short_16","alias_value":"INUO5E76B6MIIG7K","created_at":"2026-05-20T00:06:10.174845+00:00"},{"alias_kind":"pith_short_8","alias_value":"INUO5E76","created_at":"2026-05-20T00:06:10.174845+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/INUO5E76B6MIIG7KF3VIAAFQLA","json":"https://pith.science/pith/INUO5E76B6MIIG7KF3VIAAFQLA.json","graph_json":"https://pith.science/api/pith-number/INUO5E76B6MIIG7KF3VIAAFQLA/graph.json","events_json":"https://pith.science/api/pith-number/INUO5E76B6MIIG7KF3VIAAFQLA/events.json","paper":"https://pith.science/paper/INUO5E76"},"agent_actions":{"view_html":"https://pith.science/pith/INUO5E76B6MIIG7KF3VIAAFQLA","download_json":"https://pith.science/pith/INUO5E76B6MIIG7KF3VIAAFQLA.json","view_paper":"https://pith.science/paper/INUO5E76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18599&json=true","fetch_graph":"https://pith.science/api/pith-number/INUO5E76B6MIIG7KF3VIAAFQLA/graph.json","fetch_events":"https://pith.science/api/pith-number/INUO5E76B6MIIG7KF3VIAAFQLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INUO5E76B6MIIG7KF3VIAAFQLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INUO5E76B6MIIG7KF3VIAAFQLA/action/storage_attestation","attest_author":"https://pith.science/pith/INUO5E76B6MIIG7KF3VIAAFQLA/action/author_attestation","sign_citation":"https://pith.science/pith/INUO5E76B6MIIG7KF3VIAAFQLA/action/citation_signature","submit_replication":"https://pith.science/pith/INUO5E76B6MIIG7KF3VIAAFQLA/action/replication_record"}},"created_at":"2026-05-20T00:06:10.174845+00:00","updated_at":"2026-05-20T00:06:10.174845+00:00"}