{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S7JUOJXRWFWOV3ZDBTLN3Y5VLR","short_pith_number":"pith:S7JUOJXR","schema_version":"1.0","canonical_sha256":"97d34726f1b16ceaef230cd6dde3b55c4ba185c0b5803d7eb093979c4b1fffae","source":{"kind":"arxiv","id":"2605.29891","version":1},"attestation_state":"computed","paper":{"title":"DVSM: Decoder-only View Synthesis Model Done Right","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Sun, Jaesung Choe, Min-Hung Chen, Ryo Hachiuma, Yu-Chiang Frank Wang","submitted_at":"2026-05-28T13:16:09Z","abstract_excerpt":"Recent Large View Synthesis Models (LVSMs) advocate an encoder-decoder architecture that separates reconstruction and rendering into distinct networks. We re-examine this design. Through controlled experiments, we show that a decoder-only architecture, which represents scenes implicitly as a KV-cache, outperforms encoder-decoder variants while using fewer parameters at identical rendering complexity. Further analysis shows that sharing weights between the color-input reconstruction network and the camera-only rendering network better aligns their features at the same viewpoint, facilitating im"},"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":"2605.29891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T13:16:09Z","cross_cats_sorted":[],"title_canon_sha256":"d68a6ff62a537a9f48ea2a50701bb3ef8ebfc585437da1390e837502160d7a18","abstract_canon_sha256":"3492663146a4c1c34a5cc214d1913fdba495c13523af33a8ab58f57f70092f23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:58.141093Z","signature_b64":"tv1d7t2v3kVYl0wnVwRTSV9BmDfLty0LfFt5Rt6j96WfGvQow9hhZCqny3FE1gkJg+PizcgZfH4n3pjjm7R6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97d34726f1b16ceaef230cd6dde3b55c4ba185c0b5803d7eb093979c4b1fffae","last_reissued_at":"2026-05-29T02:05:58.140359Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:58.140359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DVSM: Decoder-only View Synthesis Model Done Right","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Sun, Jaesung Choe, Min-Hung Chen, Ryo Hachiuma, Yu-Chiang Frank Wang","submitted_at":"2026-05-28T13:16:09Z","abstract_excerpt":"Recent Large View Synthesis Models (LVSMs) advocate an encoder-decoder architecture that separates reconstruction and rendering into distinct networks. We re-examine this design. Through controlled experiments, we show that a decoder-only architecture, which represents scenes implicitly as a KV-cache, outperforms encoder-decoder variants while using fewer parameters at identical rendering complexity. Further analysis shows that sharing weights between the color-input reconstruction network and the camera-only rendering network better aligns their features at the same viewpoint, facilitating im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29891","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/2605.29891/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":"2605.29891","created_at":"2026-05-29T02:05:58.140477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29891v1","created_at":"2026-05-29T02:05:58.140477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29891","created_at":"2026-05-29T02:05:58.140477+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7JUOJXRWFWO","created_at":"2026-05-29T02:05:58.140477+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7JUOJXRWFWOV3ZD","created_at":"2026-05-29T02:05:58.140477+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7JUOJXR","created_at":"2026-05-29T02:05:58.140477+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/S7JUOJXRWFWOV3ZDBTLN3Y5VLR","json":"https://pith.science/pith/S7JUOJXRWFWOV3ZDBTLN3Y5VLR.json","graph_json":"https://pith.science/api/pith-number/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/graph.json","events_json":"https://pith.science/api/pith-number/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/events.json","paper":"https://pith.science/paper/S7JUOJXR"},"agent_actions":{"view_html":"https://pith.science/pith/S7JUOJXRWFWOV3ZDBTLN3Y5VLR","download_json":"https://pith.science/pith/S7JUOJXRWFWOV3ZDBTLN3Y5VLR.json","view_paper":"https://pith.science/paper/S7JUOJXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29891&json=true","fetch_graph":"https://pith.science/api/pith-number/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/graph.json","fetch_events":"https://pith.science/api/pith-number/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/action/storage_attestation","attest_author":"https://pith.science/pith/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/action/author_attestation","sign_citation":"https://pith.science/pith/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/action/citation_signature","submit_replication":"https://pith.science/pith/S7JUOJXRWFWOV3ZDBTLN3Y5VLR/action/replication_record"}},"created_at":"2026-05-29T02:05:58.140477+00:00","updated_at":"2026-05-29T02:05:58.140477+00:00"}