{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IEI6GS5FDSYRVQORSHL5YPWHWS","short_pith_number":"pith:IEI6GS5F","schema_version":"1.0","canonical_sha256":"4111e34ba51cb11ac1d191d7dc3ec7b49d76b83f6d4e362c01042e7e684edcc4","source":{"kind":"arxiv","id":"2506.05367","version":2},"attestation_state":"computed","paper":{"title":"Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aakash Garg, Andrii Tsarov, Libing Zeng, Nima Khademi Kalantari","submitted_at":"2025-05-27T22:40:35Z","abstract_excerpt":"In this paper, we propose a novel diffusion-based approach to generate stereo images given a text prompt. Since stereo image datasets with large baselines are scarce, training a diffusion model from scratch is not feasible. Therefore, we propose leveraging the strong priors learned by Stable Diffusion and fine-tuning it on stereo image datasets to adapt it to the task of stereo generation. To improve stereo consistency and text-to-image alignment, we further tune the model using prompt alignment and our proposed stereo consistency reward functions. Comprehensive experiments demonstrate the sup"},"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":"2506.05367","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T22:40:35Z","cross_cats_sorted":[],"title_canon_sha256":"8c44c29f0229952ba8086554eb73c6fe9b247f02fd60f62c193fac9bf28067f6","abstract_canon_sha256":"e97cadf331d3626df662950633e0e3073bd4249bab31b2c5725796e7f255ea15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:42.850985Z","signature_b64":"mY3jto8tXPHhRD0f8QI9jlKF/HHltPiiCEsDMvjVIaVfrzkKMb4f9KwnlrAuUXC2Ox0vfHAGc62mtTsjpaiaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4111e34ba51cb11ac1d191d7dc3ec7b49d76b83f6d4e362c01042e7e684edcc4","last_reissued_at":"2026-07-05T11:41:42.850453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:42.850453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aakash Garg, Andrii Tsarov, Libing Zeng, Nima Khademi Kalantari","submitted_at":"2025-05-27T22:40:35Z","abstract_excerpt":"In this paper, we propose a novel diffusion-based approach to generate stereo images given a text prompt. Since stereo image datasets with large baselines are scarce, training a diffusion model from scratch is not feasible. Therefore, we propose leveraging the strong priors learned by Stable Diffusion and fine-tuning it on stereo image datasets to adapt it to the task of stereo generation. To improve stereo consistency and text-to-image alignment, we further tune the model using prompt alignment and our proposed stereo consistency reward functions. Comprehensive experiments demonstrate the sup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05367","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/2506.05367/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":"2506.05367","created_at":"2026-07-05T11:41:42.850517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05367v2","created_at":"2026-07-05T11:41:42.850517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05367","created_at":"2026-07-05T11:41:42.850517+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEI6GS5FDSYR","created_at":"2026-07-05T11:41:42.850517+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEI6GS5FDSYRVQOR","created_at":"2026-07-05T11:41:42.850517+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEI6GS5F","created_at":"2026-07-05T11:41:42.850517+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/IEI6GS5FDSYRVQORSHL5YPWHWS","json":"https://pith.science/pith/IEI6GS5FDSYRVQORSHL5YPWHWS.json","graph_json":"https://pith.science/api/pith-number/IEI6GS5FDSYRVQORSHL5YPWHWS/graph.json","events_json":"https://pith.science/api/pith-number/IEI6GS5FDSYRVQORSHL5YPWHWS/events.json","paper":"https://pith.science/paper/IEI6GS5F"},"agent_actions":{"view_html":"https://pith.science/pith/IEI6GS5FDSYRVQORSHL5YPWHWS","download_json":"https://pith.science/pith/IEI6GS5FDSYRVQORSHL5YPWHWS.json","view_paper":"https://pith.science/paper/IEI6GS5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05367&json=true","fetch_graph":"https://pith.science/api/pith-number/IEI6GS5FDSYRVQORSHL5YPWHWS/graph.json","fetch_events":"https://pith.science/api/pith-number/IEI6GS5FDSYRVQORSHL5YPWHWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEI6GS5FDSYRVQORSHL5YPWHWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEI6GS5FDSYRVQORSHL5YPWHWS/action/storage_attestation","attest_author":"https://pith.science/pith/IEI6GS5FDSYRVQORSHL5YPWHWS/action/author_attestation","sign_citation":"https://pith.science/pith/IEI6GS5FDSYRVQORSHL5YPWHWS/action/citation_signature","submit_replication":"https://pith.science/pith/IEI6GS5FDSYRVQORSHL5YPWHWS/action/replication_record"}},"created_at":"2026-07-05T11:41:42.850517+00:00","updated_at":"2026-07-05T11:41:42.850517+00:00"}