{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EOQUB3BUSS26767G36XQGBA7FI","short_pith_number":"pith:EOQUB3BU","schema_version":"1.0","canonical_sha256":"23a140ec3494b5effbe6dfaf03041f2a3be3ad2c54b796c0b01835c2b5639d8c","source":{"kind":"arxiv","id":"2304.04968","version":3},"attestation_state":"computed","paper":{"title":"Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Sadeghian, Amir Sadeghian, Huangjie Zheng, Mingyuan Zhou, Mohammadreza Armandpour","submitted_at":"2023-04-11T04:29:57Z","abstract_excerpt":"Although text-to-image diffusion models have made significant strides in generating images from text, they are sometimes more inclined to generate images like the data on which the model was trained rather than the provided text. This limitation has hindered their usage in both 2D and 3D applications. To address this problem, we explored the use of negative prompts but found that the current implementation fails to produce desired results, particularly when there is an overlap between the main and negative prompts. To overcome this issue, we propose Perp-Neg, a new algorithm that leverages the"},"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":"2304.04968","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-11T04:29:57Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"91b8c2109e4befabd4c98857aff1038fdc09f8dc7bb71805b63440e86b2ddd26","abstract_canon_sha256":"4a89b191d334dd02270e53f05c8668b6f26c747ba1d494391f55780da1136506"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:37.886276Z","signature_b64":"2ovHeDxzAO93LVSg9xHcf0+INQzER4Xn6TS43PYihQzOcmmCXNhoozvn4VOnhGtPUTAbGze4xVSJ79snc48bCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23a140ec3494b5effbe6dfaf03041f2a3be3ad2c54b796c0b01835c2b5639d8c","last_reissued_at":"2026-07-05T06:04:37.885877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:37.885877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Sadeghian, Amir Sadeghian, Huangjie Zheng, Mingyuan Zhou, Mohammadreza Armandpour","submitted_at":"2023-04-11T04:29:57Z","abstract_excerpt":"Although text-to-image diffusion models have made significant strides in generating images from text, they are sometimes more inclined to generate images like the data on which the model was trained rather than the provided text. This limitation has hindered their usage in both 2D and 3D applications. To address this problem, we explored the use of negative prompts but found that the current implementation fails to produce desired results, particularly when there is an overlap between the main and negative prompts. To overcome this issue, we propose Perp-Neg, a new algorithm that leverages the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04968","kind":"arxiv","version":3},"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/2304.04968/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":"2304.04968","created_at":"2026-07-05T06:04:37.885927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04968v3","created_at":"2026-07-05T06:04:37.885927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04968","created_at":"2026-07-05T06:04:37.885927+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOQUB3BUSS26","created_at":"2026-07-05T06:04:37.885927+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOQUB3BUSS26767G","created_at":"2026-07-05T06:04:37.885927+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOQUB3BU","created_at":"2026-07-05T06:04:37.885927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03911","citing_title":"Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29964","citing_title":"Variance Reduction on the Camera Axis: Multi-View Score Distillation for 3D","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10273","citing_title":"How to Spin an Object: First, Get the Shape Right","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02316","citing_title":"ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19876","citing_title":"Structural Energy Guidance for View-Consistent Text-to-3D Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24702","citing_title":"Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03453","citing_title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16653","citing_title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13566","citing_title":"EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detection","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09071","citing_title":"Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI","json":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI.json","graph_json":"https://pith.science/api/pith-number/EOQUB3BUSS26767G36XQGBA7FI/graph.json","events_json":"https://pith.science/api/pith-number/EOQUB3BUSS26767G36XQGBA7FI/events.json","paper":"https://pith.science/paper/EOQUB3BU"},"agent_actions":{"view_html":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI","download_json":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI.json","view_paper":"https://pith.science/paper/EOQUB3BU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04968&json=true","fetch_graph":"https://pith.science/api/pith-number/EOQUB3BUSS26767G36XQGBA7FI/graph.json","fetch_events":"https://pith.science/api/pith-number/EOQUB3BUSS26767G36XQGBA7FI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI/action/storage_attestation","attest_author":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI/action/author_attestation","sign_citation":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI/action/citation_signature","submit_replication":"https://pith.science/pith/EOQUB3BUSS26767G36XQGBA7FI/action/replication_record"}},"created_at":"2026-07-05T06:04:37.885927+00:00","updated_at":"2026-07-05T06:04:37.885927+00:00"}