{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2NHBPVMDFKRUQHHVIYCUBJPPGV","short_pith_number":"pith:2NHBPVMD","schema_version":"1.0","canonical_sha256":"d34e17d5832aa3481cf5460540a5ef357e50e88da939bb4d37d480c6106851e0","source":{"kind":"arxiv","id":"2405.11252","version":1},"attestation_state":"computed","paper":{"title":"Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Duan, Jun Song, Rajiv Ranjan, Tejal Shah, Varun Ojha, Xingyu Miao, Yang Long","submitted_at":"2024-05-18T10:41:57Z","abstract_excerpt":"In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval Score Matching (ISM) when using the Denoising Diffusion Implicit Models (DDIM) inversion process. Unlike ISM which adopts the inversion process of DDIM to calculate on a single path, our TSM method leverages the inversion process of DDIM to generate two paths from the same starting point for calculation. Since both paths start from the same starting point, TSM can reduce the accumulated error compared to ISM, thus a"},"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":"2405.11252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-18T10:41:57Z","cross_cats_sorted":[],"title_canon_sha256":"268778e7536c8877aed849ff712eafc84c6d3927c846b03f229c1d8982e51c89","abstract_canon_sha256":"961d46331e3f81be6e5165233f9667fbf05c8ba3c61a18fe8d809be2533ba4f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:35.836595Z","signature_b64":"CUCTDIiWIH9o3BApyCpmCNKheZ26OQv29nqbWnn8m5bSaf6g4qdJLQlxoEArd8hpnm6WuMmK++Jj/SRtiaEXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d34e17d5832aa3481cf5460540a5ef357e50e88da939bb4d37d480c6106851e0","last_reissued_at":"2026-07-05T08:20:35.836050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:35.836050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Duan, Jun Song, Rajiv Ranjan, Tejal Shah, Varun Ojha, Xingyu Miao, Yang Long","submitted_at":"2024-05-18T10:41:57Z","abstract_excerpt":"In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval Score Matching (ISM) when using the Denoising Diffusion Implicit Models (DDIM) inversion process. Unlike ISM which adopts the inversion process of DDIM to calculate on a single path, our TSM method leverages the inversion process of DDIM to generate two paths from the same starting point for calculation. Since both paths start from the same starting point, TSM can reduce the accumulated error compared to ISM, thus a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11252","kind":"arxiv","version":1},"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/2405.11252/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":"2405.11252","created_at":"2026-07-05T08:20:35.836123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11252v1","created_at":"2026-07-05T08:20:35.836123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11252","created_at":"2026-07-05T08:20:35.836123+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NHBPVMDFKRU","created_at":"2026-07-05T08:20:35.836123+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NHBPVMDFKRUQHHV","created_at":"2026-07-05T08:20:35.836123+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NHBPVMD","created_at":"2026-07-05T08:20:35.836123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.02316","citing_title":"ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20872","citing_title":"CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":191,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV","json":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV.json","graph_json":"https://pith.science/api/pith-number/2NHBPVMDFKRUQHHVIYCUBJPPGV/graph.json","events_json":"https://pith.science/api/pith-number/2NHBPVMDFKRUQHHVIYCUBJPPGV/events.json","paper":"https://pith.science/paper/2NHBPVMD"},"agent_actions":{"view_html":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV","download_json":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV.json","view_paper":"https://pith.science/paper/2NHBPVMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11252&json=true","fetch_graph":"https://pith.science/api/pith-number/2NHBPVMDFKRUQHHVIYCUBJPPGV/graph.json","fetch_events":"https://pith.science/api/pith-number/2NHBPVMDFKRUQHHVIYCUBJPPGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV/action/storage_attestation","attest_author":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV/action/author_attestation","sign_citation":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV/action/citation_signature","submit_replication":"https://pith.science/pith/2NHBPVMDFKRUQHHVIYCUBJPPGV/action/replication_record"}},"created_at":"2026-07-05T08:20:35.836123+00:00","updated_at":"2026-07-05T08:20:35.836123+00:00"}