{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BAIJB5ZUMPBD2SG2AC4MQTWQAX","short_pith_number":"pith:BAIJB5ZU","schema_version":"1.0","canonical_sha256":"081090f73463c23d48da00b8c84ed005fcd3617a69ef4c70adb3a8f7060ab77d","source":{"kind":"arxiv","id":"2506.13594","version":1},"attestation_state":"computed","paper":{"title":"Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Sun, Weijian Luo, Weimin Bai, Wenzheng Chen, Yubo Li","submitted_at":"2025-06-16T15:21:30Z","abstract_excerpt":"Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis. However, existing methods typically rely on Score Distillation Sampling (SDS) loss, which involves asymmetric KL divergence--a formulation that inherently favors mode-seeking behavior and limits generation diversity. In this paper, we introduce Dive3D, a novel text-to-3D generation framework that replaces KL-based objectives with Score Implicit Matching (SIM) loss, a score-based objective that effectively mitigates mode collapse. Furthermore, Dive3D integrates both diffusion distil"},"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":"2506.13594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-16T15:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"66c696b43e4bc139bc3638996739976869a17117fb28c5f22360427b3bfeb1bf","abstract_canon_sha256":"d8dfb47690b3d269a666cff3610eafacce830bfe2d80fe3e4da03c54ba60c99f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:23.032627Z","signature_b64":"UShEdXtsLlHTbFBHa5FxCych5GhBE+fEyJ+6Y35lYdox5Dzq9MjknkwTK8j7ZFIePG9Fr223v4V2zf2GaB5jBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"081090f73463c23d48da00b8c84ed005fcd3617a69ef4c70adb3a8f7060ab77d","last_reissued_at":"2026-07-05T11:22:23.032130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:23.032130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Sun, Weijian Luo, Weimin Bai, Wenzheng Chen, Yubo Li","submitted_at":"2025-06-16T15:21:30Z","abstract_excerpt":"Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis. However, existing methods typically rely on Score Distillation Sampling (SDS) loss, which involves asymmetric KL divergence--a formulation that inherently favors mode-seeking behavior and limits generation diversity. In this paper, we introduce Dive3D, a novel text-to-3D generation framework that replaces KL-based objectives with Score Implicit Matching (SIM) loss, a score-based objective that effectively mitigates mode collapse. Furthermore, Dive3D integrates both diffusion distil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13594","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/2506.13594/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":"2506.13594","created_at":"2026-07-05T11:22:23.032191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13594v1","created_at":"2026-07-05T11:22:23.032191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13594","created_at":"2026-07-05T11:22:23.032191+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAIJB5ZUMPBD","created_at":"2026-07-05T11:22:23.032191+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAIJB5ZUMPBD2SG2","created_at":"2026-07-05T11:22:23.032191+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAIJB5ZU","created_at":"2026-07-05T11:22:23.032191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25042","citing_title":"Unbiased Diffusion Variational Inversion via Principled Posterior Matching","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX","json":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX.json","graph_json":"https://pith.science/api/pith-number/BAIJB5ZUMPBD2SG2AC4MQTWQAX/graph.json","events_json":"https://pith.science/api/pith-number/BAIJB5ZUMPBD2SG2AC4MQTWQAX/events.json","paper":"https://pith.science/paper/BAIJB5ZU"},"agent_actions":{"view_html":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX","download_json":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX.json","view_paper":"https://pith.science/paper/BAIJB5ZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13594&json=true","fetch_graph":"https://pith.science/api/pith-number/BAIJB5ZUMPBD2SG2AC4MQTWQAX/graph.json","fetch_events":"https://pith.science/api/pith-number/BAIJB5ZUMPBD2SG2AC4MQTWQAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX/action/storage_attestation","attest_author":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX/action/author_attestation","sign_citation":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX/action/citation_signature","submit_replication":"https://pith.science/pith/BAIJB5ZUMPBD2SG2AC4MQTWQAX/action/replication_record"}},"created_at":"2026-07-05T11:22:23.032191+00:00","updated_at":"2026-07-05T11:22:23.032191+00:00"}