{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5N6ADO44OLXCN2T2HZYL76VSZ4","short_pith_number":"pith:5N6ADO44","schema_version":"1.0","canonical_sha256":"eb7c01bb9c72ee26ea7a3e70bffab2cf048f15acca650116b19e892f062578f9","source":{"kind":"arxiv","id":"2508.20470","version":1},"attestation_state":"computed","paper":{"title":"Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyu Fan, Changsheng Li, Guoguang Du, Haiyang Liu, Liang Jin, Lihua Lu, Qi Jia, RenGang Li, Runze Zhang, Tianqi Wang, Xiaochuan Li, Xiaoli Gong, YaQian Zhao, Zhenhua Guo","submitted_at":"2025-08-28T06:39:41Z","abstract_excerpt":"Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data scarcity in the 3D domain, as there is far less of it available on the internet compared to the aforementioned modalities. Fortunately, there exist adequate videos that inherently contain commonsense priors, offering an alternative supervisory signal to mitigate the generalization bottleneck caused by limited native 3D data. On the one hand, videos capturing multiple views of an object or scene provide a spatial consist"},"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":"2508.20470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T06:39:41Z","cross_cats_sorted":[],"title_canon_sha256":"11de56182be1ef49535c24c9ea4a528dc99a89f53f0fd7923b6578e0a5491735","abstract_canon_sha256":"5998148fc4dd1c5b8cc1107cad797fe596c689b221beb4b727fdc4bf92a75f94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:52.723116Z","signature_b64":"KecBhKXuD4iM7stzYjaXS5ErwVoq4Z3NzSZA0PlvbsAbTlMjqbgPj8nnAv6nj4LJ0A4oAbtL1d3lNVvqAJ38BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb7c01bb9c72ee26ea7a3e70bffab2cf048f15acca650116b19e892f062578f9","last_reissued_at":"2026-07-05T12:00:52.722586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:52.722586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyu Fan, Changsheng Li, Guoguang Du, Haiyang Liu, Liang Jin, Lihua Lu, Qi Jia, RenGang Li, Runze Zhang, Tianqi Wang, Xiaochuan Li, Xiaoli Gong, YaQian Zhao, Zhenhua Guo","submitted_at":"2025-08-28T06:39:41Z","abstract_excerpt":"Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data scarcity in the 3D domain, as there is far less of it available on the internet compared to the aforementioned modalities. Fortunately, there exist adequate videos that inherently contain commonsense priors, offering an alternative supervisory signal to mitigate the generalization bottleneck caused by limited native 3D data. On the one hand, videos capturing multiple views of an object or scene provide a spatial consist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20470","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/2508.20470/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":"2508.20470","created_at":"2026-07-05T12:00:52.722652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20470v1","created_at":"2026-07-05T12:00:52.722652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20470","created_at":"2026-07-05T12:00:52.722652+00:00"},{"alias_kind":"pith_short_12","alias_value":"5N6ADO44OLXC","created_at":"2026-07-05T12:00:52.722652+00:00"},{"alias_kind":"pith_short_16","alias_value":"5N6ADO44OLXCN2T2","created_at":"2026-07-05T12:00:52.722652+00:00"},{"alias_kind":"pith_short_8","alias_value":"5N6ADO44","created_at":"2026-07-05T12:00:52.722652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20539","citing_title":"Animator-Centric Skeleton Generation on Objects with Fine-Grained Details","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4","json":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4.json","graph_json":"https://pith.science/api/pith-number/5N6ADO44OLXCN2T2HZYL76VSZ4/graph.json","events_json":"https://pith.science/api/pith-number/5N6ADO44OLXCN2T2HZYL76VSZ4/events.json","paper":"https://pith.science/paper/5N6ADO44"},"agent_actions":{"view_html":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4","download_json":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4.json","view_paper":"https://pith.science/paper/5N6ADO44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20470&json=true","fetch_graph":"https://pith.science/api/pith-number/5N6ADO44OLXCN2T2HZYL76VSZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/5N6ADO44OLXCN2T2HZYL76VSZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4/action/storage_attestation","attest_author":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4/action/author_attestation","sign_citation":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4/action/citation_signature","submit_replication":"https://pith.science/pith/5N6ADO44OLXCN2T2HZYL76VSZ4/action/replication_record"}},"created_at":"2026-07-05T12:00:52.722652+00:00","updated_at":"2026-07-05T12:00:52.722652+00:00"}