{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V4FL6PO4WAWXZMQT5EVJ3IHBNT","short_pith_number":"pith:V4FL6PO4","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"},"canonical_sha256":"af0abf3ddcb02d7cb213e92a9da0e16cf99a77ddc18b48247d115976316299ed","source":{"kind":"arxiv","id":"2605.12938","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12938","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12938v1","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12938","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"V4FL6PO4WAWX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"V4FL6PO4WAWXZMQT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"V4FL6PO4","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V4FL6PO4WAWXZMQT5EVJ3IHBNT","target":"record","payload":{"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"},"canonical_sha256":"af0abf3ddcb02d7cb213e92a9da0e16cf99a77ddc18b48247d115976316299ed","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"},"source_kind":"arxiv","source_id":"2605.12938","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFAzP2VPF1pJavKJf3KxxdXblt6zAloujCPJcN+jJKpZHfXQPqD8eOnaDWMqPU3EIAj3WXua5PDVd5VYH75SAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:24:03.773235Z"},"content_sha256":"86e6a368cc05a576f6482a275964c66436708903398015006a4fbecae1245a5b","schema_version":"1.0","event_id":"sha256:86e6a368cc05a576f6482a275964c66436708903398015006a4fbecae1245a5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V4FL6PO4WAWXZMQT5EVJ3IHBNT","target":"graph","payload":{"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"},"verdict_id":"c3150c16-f3c2-4359-b597-1ddac2005e8b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8FlHr8gzpUO+Z7RM8eQtxjolGDbbbr4+q/APtgyt003T+sCvvjBbKgbc+Mdn59Mb5u+JXsIwW9h0XYTckcRnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:24:03.773866Z"},"content_sha256":"319403e56f9112ec93b2ecf69c522f23880fbc2e3c8d58b5c7eca93a2c85f797","schema_version":"1.0","event_id":"sha256:319403e56f9112ec93b2ecf69c522f23880fbc2e3c8d58b5c7eca93a2c85f797"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/bundle.json","state_url":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T14:24:03Z","links":{"resolver":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT","bundle":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/bundle.json","state":"https://pith.science/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4FL6PO4WAWXZMQT5EVJ3IHBNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V4FL6PO4WAWXZMQT5EVJ3IHBNT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ee6199ccfdebabad850cf19d4e2cd84f9bdf0fdec5e359727c0dbc898ed87941","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:18:26Z","title_canon_sha256":"c5e7d9115f62391d5b76f146cb8bbbb3291533718a712df587f99e2ee46bc3dc"},"schema_version":"1.0","source":{"id":"2605.12938","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12938","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12938v1","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12938","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"V4FL6PO4WAWX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"V4FL6PO4WAWXZMQT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"V4FL6PO4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:319403e56f9112ec93b2ecf69c522f23880fbc2e3c8d58b5c7eca93a2c85f797","target":"graph","created_at":"2026-05-18T03:09:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CRePE supplies depth-aware positional distributions along curved rays for stable unified-camera control in frozen video DiT models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"632fe6cff5c5ae1917b661fb5c1bc316ad5d8d6a7ce1374b0118791e84699e75"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fa861051cd04929a8de81537a17ff8316cc369c0b46c6105fb0a58cd0d6310e8"},"paper":{"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","authors_text":"Jong Chul Ye, Seonghyun Jin, Sunwoo Park, Youngmin Kim","cross_cats":["cs.AI","cs.LG"],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:18:26Z","title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation"},"references":{"count":24,"internal_anchors":3,"resolved_work":24,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Recammaster: Camera-controlled generative rendering from a single video","work_id":"d26e2d77-d93f-42ea-83d3-eb5325fe30d4","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2601.15275 (2026) 4, 8, 9, 21","work_id":"51636ad9-ac46-4382-bea0-d73080115ee4","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"arXiv preprint arXiv:2512.07237 (2025)","work_id":"59c944cc-e7b5-4565-84db-e5b36b9aeef5","year":2025},{"cited_arxiv_id":"2212.09748","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Scalable Diffusion Models with Transformers","work_id":"a3a05169-18b1-42bb-8775-eada50163437","year":2023},{"cited_arxiv_id":"2503.20314","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","year":2025}],"snapshot_sha256":"65d65b48e59bfd895c0057157d23a675fda24961fb87df36b2fe54d79f6df34e"},"source":{"id":"2605.12938","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:02:32.921479Z","id":"c3150c16-f3c2-4359-b597-1ddac2005e8b","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"c3150c16-f3c2-4359-b597-1ddac2005e8b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:86e6a368cc05a576f6482a275964c66436708903398015006a4fbecae1245a5b","target":"record","created_at":"2026-05-18T03:09:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ee6199ccfdebabad850cf19d4e2cd84f9bdf0fdec5e359727c0dbc898ed87941","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:18:26Z","title_canon_sha256":"c5e7d9115f62391d5b76f146cb8bbbb3291533718a712df587f99e2ee46bc3dc"},"schema_version":"1.0","source":{"id":"2605.12938","kind":"arxiv","version":1}},"canonical_sha256":"af0abf3ddcb02d7cb213e92a9da0e16cf99a77ddc18b48247d115976316299ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af0abf3ddcb02d7cb213e92a9da0e16cf99a77ddc18b48247d115976316299ed","first_computed_at":"2026-05-18T03:09:09.786681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:09.786681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nB2S7sOXgyt7yHTAVt2uQQUxlg/7ePi7hWsLRY1bl+bQZOWV2pLHq/AzvVfDxlLKpFv3w3Y5zYT8n7XliQjtAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:09.787760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12938","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86e6a368cc05a576f6482a275964c66436708903398015006a4fbecae1245a5b","sha256:319403e56f9112ec93b2ecf69c522f23880fbc2e3c8d58b5c7eca93a2c85f797"],"state_sha256":"060913b394d674607b1a92701a8f365189b67ef772336305765b0aa5794afb1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SDcpa0UvPRAjMKUlKTUdF3Lb/FzgtfFKQm0QPLZNBD0Hauvfgy8WSN1ubVFhTCmPY0XuWEjUZrvhi0hB8zvRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T14:24:03.776552Z","bundle_sha256":"2aede5f82a927697a6a26d610ee86ba3222d21cdd8b141ff0fdb799715979573"}}