{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V4FL6PO4WAWXZMQT5EVJ3IHBNT","short_pith_number":"pith:V4FL6PO4","schema_version":"1.0","canonical_sha256":"af0abf3ddcb02d7cb213e92a9da0e16cf99a77ddc18b48247d115976316299ed","source":{"kind":"arxiv","id":"2605.12938","version":1},"attestation_state":"computed","paper":{"title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CRePE represents each image token as a depth-aware positional distribution along its source ray to support unified camera control under the Unified Camera Model.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jong Chul Ye, Seonghyun Jin, Sunwoo Park, Youngmin Kim","submitted_at":"2026-05-13T03:18:26Z","abstract_excerpt":"Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either provide ray-only camera signals or rely on pinhole camera geometry, limiting their applicability to general camera control under the Unified Camera Model, including wide-angle and fisheye lenses. To address this limitation, we propose Curved Ray Expectation Positional Encoding (CRePE). CRePE represents each image token as a depth-aware positional distribution along its source ray"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12938","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:18:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c5e7d9115f62391d5b76f146cb8bbbb3291533718a712df587f99e2ee46bc3dc","abstract_canon_sha256":"ee6199ccfdebabad850cf19d4e2cd84f9bdf0fdec5e359727c0dbc898ed87941"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:09.787760Z","signature_b64":"nB2S7sOXgyt7yHTAVt2uQQUxlg/7ePi7hWsLRY1bl+bQZOWV2pLHq/AzvVfDxlLKpFv3w3Y5zYT8n7XliQjtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af0abf3ddcb02d7cb213e92a9da0e16cf99a77ddc18b48247d115976316299ed","last_reissued_at":"2026-05-18T03:09:09.786681Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:09.786681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CRePE represents each image token as a depth-aware positional distribution along its source ray to support unified camera control under the Unified Camera Model.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jong Chul Ye, Seonghyun Jin, Sunwoo Park, Youngmin Kim","submitted_at":"2026-05-13T03:18:26Z","abstract_excerpt":"Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either provide ray-only camera signals or rely on pinhole camera geometry, limiting their applicability to general camera control under the Unified Camera Model, including wide-angle and fisheye lenses. To address this limitation, we propose Curved Ray Expectation Positional Encoding (CRePE). CRePE represents each image token as a depth-aware positional distribution along its source ray"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CRePE represents each image token as a depth-aware positional distribution along its source ray, providing a Unified Camera Model-compatible positional encoding that captures the projected-path geometry induced by wide-angle and fisheye cameras.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That pseudo-supervision from a monocular geometry foundation model is sufficient to stabilize the Geometric Attention Adapter without introducing systematic bias in the learned ray distributions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CRePE supplies depth-aware positional distributions along curved rays for stable unified-camera control in frozen video DiT models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CRePE represents each image token as a depth-aware positional distribution along its source ray to support unified camera control under the Unified Camera Model.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"632fe6cff5c5ae1917b661fb5c1bc316ad5d8d6a7ce1374b0118791e84699e75"},"source":{"id":"2605.12938","kind":"arxiv","version":1},"verdict":{"id":"c3150c16-f3c2-4359-b597-1ddac2005e8b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:02:32.921479Z","strongest_claim":"CRePE represents each image token as a depth-aware positional distribution along its source ray, providing a Unified Camera Model-compatible positional encoding that captures the projected-path geometry induced by wide-angle and fisheye cameras.","one_line_summary":"CRePE supplies depth-aware positional distributions along curved rays for stable unified-camera control in frozen video DiT models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That pseudo-supervision from a monocular geometry foundation model is sufficient to stabilize the Geometric Attention Adapter without introducing systematic bias in the learned ray distributions.","pith_extraction_headline":"CRePE represents each image token as a depth-aware positional distribution along its source ray to support unified camera control under the Unified Camera Model."},"references":{"count":24,"sample":[{"doi":"","year":2025,"title":"Recammaster: Camera-controlled generative rendering from a single video","work_id":"d26e2d77-d93f-42ea-83d3-eb5325fe30d4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"arXiv preprint arXiv:2601.15275 (2026) 4, 8, 9, 21","work_id":"51636ad9-ac46-4382-bea0-d73080115ee4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"arXiv preprint arXiv:2512.07237 (2025)","work_id":"59c944cc-e7b5-4565-84db-e5b36b9aeef5","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Scalable Diffusion Models with Transformers","work_id":"a3a05169-18b1-42bb-8775-eada50163437","ref_index":4,"cited_arxiv_id":"2212.09748","is_internal_anchor":true},{"doi":"","year":2025,"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","ref_index":5,"cited_arxiv_id":"2503.20314","is_internal_anchor":true}],"resolved_work":24,"snapshot_sha256":"65d65b48e59bfd895c0057157d23a675fda24961fb87df36b2fe54d79f6df34e","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fa861051cd04929a8de81537a17ff8316cc369c0b46c6105fb0a58cd0d6310e8"},"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":"2605.12938","created_at":"2026-05-18T03:09:09.786893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12938v1","created_at":"2026-05-18T03:09:09.786893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12938","created_at":"2026-05-18T03:09:09.786893+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4FL6PO4WAWX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4FL6PO4WAWXZMQT","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4FL6PO4","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT","json":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT.json","graph_json":"https://pith.science/api/pith-number/V4FL6PO4WAWXZMQT5EVJ3IHBNT/graph.json","events_json":"https://pith.science/api/pith-number/V4FL6PO4WAWXZMQT5EVJ3IHBNT/events.json","paper":"https://pith.science/paper/V4FL6PO4"},"agent_actions":{"view_html":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT","download_json":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT.json","view_paper":"https://pith.science/paper/V4FL6PO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12938&json=true","fetch_graph":"https://pith.science/api/pith-number/V4FL6PO4WAWXZMQT5EVJ3IHBNT/graph.json","fetch_events":"https://pith.science/api/pith-number/V4FL6PO4WAWXZMQT5EVJ3IHBNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/action/storage_attestation","attest_author":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/action/author_attestation","sign_citation":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/action/citation_signature","submit_replication":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/action/replication_record"}},"created_at":"2026-05-18T03:09:09.786893+00:00","updated_at":"2026-05-18T03:09:09.786893+00:00"}