{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QBTJ54NXLA2H5DFMS4QLGVGDNK","short_pith_number":"pith:QBTJ54NX","schema_version":"1.0","canonical_sha256":"80669ef1b758347e8cac9720b354c36aad4375b2dd724aa5dbb0794d43df5dc2","source":{"kind":"arxiv","id":"2410.21299","version":2},"attestation_state":"computed","paper":{"title":"TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Donglin Di, Jiahui Yang, Jianxun Cui, Meng Wang, Wei Chen, Wenzhang Sun, Xun Yang, Yebin Liu, Yongjia Ma, Zhou Xue","submitted_at":"2024-10-16T07:13:09Z","abstract_excerpt":"In recent years, advancements in generative models have significantly expanded the capabilities of text-to-3D generation. Many approaches rely on Score Distillation Sampling (SDS) technology. However, SDS struggles to accommodate multi-condition inputs, such as text and visual prompts, in customized generation tasks. To explore the core reasons, we decompose SDS into a difference term and a classifier-free guidance term. Our analysis identifies the core issue as arising from the difference term and the random noise addition during the optimization process, both contributing to deviations from "},"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":"2410.21299","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T07:13:09Z","cross_cats_sorted":[],"title_canon_sha256":"7f851c8f0789cda042b33388cdf702a94d30d0b19bf7e823c3b8346fd87da93d","abstract_canon_sha256":"4f0f2f53f2efe627122375230adbfa66b928945913edc66e797ad128bb1d7843"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:57.134851Z","signature_b64":"Q3J824Tnq6hvUjBhq5AeST1nk0WJetmmQ9DZUUMVBD4/zhrJzik4pmlplPYmnYhRab0DuAty/IW9HSVXNSU6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80669ef1b758347e8cac9720b354c36aad4375b2dd724aa5dbb0794d43df5dc2","last_reissued_at":"2026-07-05T09:28:57.134350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:57.134350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Donglin Di, Jiahui Yang, Jianxun Cui, Meng Wang, Wei Chen, Wenzhang Sun, Xun Yang, Yebin Liu, Yongjia Ma, Zhou Xue","submitted_at":"2024-10-16T07:13:09Z","abstract_excerpt":"In recent years, advancements in generative models have significantly expanded the capabilities of text-to-3D generation. Many approaches rely on Score Distillation Sampling (SDS) technology. However, SDS struggles to accommodate multi-condition inputs, such as text and visual prompts, in customized generation tasks. To explore the core reasons, we decompose SDS into a difference term and a classifier-free guidance term. Our analysis identifies the core issue as arising from the difference term and the random noise addition during the optimization process, both contributing to deviations from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21299","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/2410.21299/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":"2410.21299","created_at":"2026-07-05T09:28:57.134409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21299v2","created_at":"2026-07-05T09:28:57.134409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21299","created_at":"2026-07-05T09:28:57.134409+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBTJ54NXLA2H","created_at":"2026-07-05T09:28:57.134409+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBTJ54NXLA2H5DFM","created_at":"2026-07-05T09:28:57.134409+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBTJ54NX","created_at":"2026-07-05T09:28:57.134409+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/QBTJ54NXLA2H5DFMS4QLGVGDNK","json":"https://pith.science/pith/QBTJ54NXLA2H5DFMS4QLGVGDNK.json","graph_json":"https://pith.science/api/pith-number/QBTJ54NXLA2H5DFMS4QLGVGDNK/graph.json","events_json":"https://pith.science/api/pith-number/QBTJ54NXLA2H5DFMS4QLGVGDNK/events.json","paper":"https://pith.science/paper/QBTJ54NX"},"agent_actions":{"view_html":"https://pith.science/pith/QBTJ54NXLA2H5DFMS4QLGVGDNK","download_json":"https://pith.science/pith/QBTJ54NXLA2H5DFMS4QLGVGDNK.json","view_paper":"https://pith.science/paper/QBTJ54NX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21299&json=true","fetch_graph":"https://pith.science/api/pith-number/QBTJ54NXLA2H5DFMS4QLGVGDNK/graph.json","fetch_events":"https://pith.science/api/pith-number/QBTJ54NXLA2H5DFMS4QLGVGDNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBTJ54NXLA2H5DFMS4QLGVGDNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBTJ54NXLA2H5DFMS4QLGVGDNK/action/storage_attestation","attest_author":"https://pith.science/pith/QBTJ54NXLA2H5DFMS4QLGVGDNK/action/author_attestation","sign_citation":"https://pith.science/pith/QBTJ54NXLA2H5DFMS4QLGVGDNK/action/citation_signature","submit_replication":"https://pith.science/pith/QBTJ54NXLA2H5DFMS4QLGVGDNK/action/replication_record"}},"created_at":"2026-07-05T09:28:57.134409+00:00","updated_at":"2026-07-05T09:28:57.134409+00:00"}