{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NU5KHMMYPGTGO3ADYEF5IFW6JZ","short_pith_number":"pith:NU5KHMMY","canonical_record":{"source":{"id":"2309.07986","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T18:52:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a5b528b56785c07fa71940dde01631fdd11a369bfc3f1f5c82401c47c2fcd093","abstract_canon_sha256":"3fe2a3b9e0a90cfb3e7779e5ed595c8d6e0c5f056892fe34a19727d74be1eb21"},"schema_version":"1.0"},"canonical_sha256":"6d3aa3b19879a6676c03c10bd416de4e5325785818df877d22c7f0c494d2da6e","source":{"kind":"arxiv","id":"2309.07986","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07986","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07986v2","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07986","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"NU5KHMMYPGTG","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"pith_short_16","alias_value":"NU5KHMMYPGTGO3AD","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"pith_short_8","alias_value":"NU5KHMMY","created_at":"2026-07-05T08:48:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NU5KHMMYPGTGO3ADYEF5IFW6JZ","target":"record","payload":{"canonical_record":{"source":{"id":"2309.07986","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T18:52:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a5b528b56785c07fa71940dde01631fdd11a369bfc3f1f5c82401c47c2fcd093","abstract_canon_sha256":"3fe2a3b9e0a90cfb3e7779e5ed595c8d6e0c5f056892fe34a19727d74be1eb21"},"schema_version":"1.0"},"canonical_sha256":"6d3aa3b19879a6676c03c10bd416de4e5325785818df877d22c7f0c494d2da6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:39.312148Z","signature_b64":"eUliFTyJweDHee4iVbNH2z9FH9KoEMvYaPkZe+xEJpxIGFrpIvRCC39NhzoiQLQTUOqRSEBcQALOMOOwD5UeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d3aa3b19879a6676c03c10bd416de4e5325785818df877d22c7f0c494d2da6e","last_reissued_at":"2026-07-05T08:48:39.311692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:39.311692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.07986","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iDtpZEiEqhpA3py62QaHJ2jbmskId7fTnzaxig6tJwCDaTG6URhVBn3JQDDhlHAi2HZwXUG53yT17n/rTYUoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:49:50.267628Z"},"content_sha256":"043b7cf4c05d04f6061679fa4957b85eef61a1e26e00e50bff686f0e0aea47be","schema_version":"1.0","event_id":"sha256:043b7cf4c05d04f6061679fa4957b85eef61a1e26e00e50bff686f0e0aea47be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NU5KHMMYPGTGO3ADYEF5IFW6JZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"James Burgess, Kuan-Chieh Wang, Serena Yeung-Levy","submitted_at":"2023-09-14T18:52:16Z","abstract_excerpt":"Text-to-image diffusion models generate impressive and realistic images, but do they learn to represent the 3D world from only 2D supervision? We demonstrate that yes, certain 3D scene representations are encoded in the text embedding space of models like Stable Diffusion. Our approach, Viewpoint Neural Textual Inversion (ViewNeTI), is to discover 3D view tokens; these tokens control the 3D viewpoint - the rendering pose in a scene - of generated images. Specifically, we train a small neural mapper to take continuous camera viewpoint parameters and predict a view token (a word embedding). This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07986","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/2309.07986/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rmUvYscs4oaW+bJVIXz68b4QNNNVX4xKcRVu4WO5VrLVO+3KJtc36DOrUJZADI21wYGbfvAhHat5V9CBUv/DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:49:50.268291Z"},"content_sha256":"9f50dc46e2c5ca70b842dab5d7270cf09a05b0771e8cbd84e2b1c42357a4dbc0","schema_version":"1.0","event_id":"sha256:9f50dc46e2c5ca70b842dab5d7270cf09a05b0771e8cbd84e2b1c42357a4dbc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NU5KHMMYPGTGO3ADYEF5IFW6JZ/bundle.json","state_url":"https://pith.science/pith/NU5KHMMYPGTGO3ADYEF5IFW6JZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NU5KHMMYPGTGO3ADYEF5IFW6JZ/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":"2026-08-12T23:49:50Z","links":{"resolver":"https://pith.science/pith/NU5KHMMYPGTGO3ADYEF5IFW6JZ","bundle":"https://pith.science/pith/NU5KHMMYPGTGO3ADYEF5IFW6JZ/bundle.json","state":"https://pith.science/pith/NU5KHMMYPGTGO3ADYEF5IFW6JZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NU5KHMMYPGTGO3ADYEF5IFW6JZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NU5KHMMYPGTGO3ADYEF5IFW6JZ","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":"3fe2a3b9e0a90cfb3e7779e5ed595c8d6e0c5f056892fe34a19727d74be1eb21","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T18:52:16Z","title_canon_sha256":"a5b528b56785c07fa71940dde01631fdd11a369bfc3f1f5c82401c47c2fcd093"},"schema_version":"1.0","source":{"id":"2309.07986","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07986","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07986v2","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07986","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"NU5KHMMYPGTG","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"pith_short_16","alias_value":"NU5KHMMYPGTGO3AD","created_at":"2026-07-05T08:48:39Z"},{"alias_kind":"pith_short_8","alias_value":"NU5KHMMY","created_at":"2026-07-05T08:48:39Z"}],"graph_snapshots":[{"event_id":"sha256:9f50dc46e2c5ca70b842dab5d7270cf09a05b0771e8cbd84e2b1c42357a4dbc0","target":"graph","created_at":"2026-07-05T08:48:39Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.07986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image diffusion models generate impressive and realistic images, but do they learn to represent the 3D world from only 2D supervision? We demonstrate that yes, certain 3D scene representations are encoded in the text embedding space of models like Stable Diffusion. Our approach, Viewpoint Neural Textual Inversion (ViewNeTI), is to discover 3D view tokens; these tokens control the 3D viewpoint - the rendering pose in a scene - of generated images. Specifically, we train a small neural mapper to take continuous camera viewpoint parameters and predict a view token (a word embedding). This","authors_text":"James Burgess, Kuan-Chieh Wang, Serena Yeung-Levy","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T18:52:16Z","title":"Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07986","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:043b7cf4c05d04f6061679fa4957b85eef61a1e26e00e50bff686f0e0aea47be","target":"record","created_at":"2026-07-05T08:48:39Z","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":"3fe2a3b9e0a90cfb3e7779e5ed595c8d6e0c5f056892fe34a19727d74be1eb21","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T18:52:16Z","title_canon_sha256":"a5b528b56785c07fa71940dde01631fdd11a369bfc3f1f5c82401c47c2fcd093"},"schema_version":"1.0","source":{"id":"2309.07986","kind":"arxiv","version":2}},"canonical_sha256":"6d3aa3b19879a6676c03c10bd416de4e5325785818df877d22c7f0c494d2da6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d3aa3b19879a6676c03c10bd416de4e5325785818df877d22c7f0c494d2da6e","first_computed_at":"2026-07-05T08:48:39.311692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:39.311692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eUliFTyJweDHee4iVbNH2z9FH9KoEMvYaPkZe+xEJpxIGFrpIvRCC39NhzoiQLQTUOqRSEBcQALOMOOwD5UeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:39.312148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07986","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:043b7cf4c05d04f6061679fa4957b85eef61a1e26e00e50bff686f0e0aea47be","sha256:9f50dc46e2c5ca70b842dab5d7270cf09a05b0771e8cbd84e2b1c42357a4dbc0"],"state_sha256":"2289068b120ebdb0b6e12a1338703424d43fab25f03f94a60dac7f607173ed40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urn5C6Gbty80/sr6uhje0aPz48OQ7M5RQKmZZK9KjOxdbSLfZBa/3sh7vhZFMdx1VlaC3T1CWDRTz36STk42Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:49:50.272701Z","bundle_sha256":"b4a90ba8eb2e207a781d1697df4147c8b48c6a930d30a52414a26d128c7c8461"}}