{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JFDVVLXBPNORZV2FDLHRYFUTUJ","short_pith_number":"pith:JFDVVLXB","schema_version":"1.0","canonical_sha256":"49475aaee17b5d1cd7451acf1c1693a25d6ea79e2393aafb12224dd8d38d423a","source":{"kind":"arxiv","id":"2404.06091","version":1},"attestation_state":"computed","paper":{"title":"Hash3D: Training-free Acceleration for 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinchao Wang, Xingyi Yang","submitted_at":"2024-04-09T07:49:30Z","abstract_excerpt":"The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se presents a critical hurdle to efficiency. In this paper, we introduce Hash3D, a universal acceleration for 3D generation without model training. Central to Hash3D is the insight that feature-map redundancy is prevalent in images rendered from camera positions and diffusion time-steps in close proximity. By effectively hashing and reusing these feature maps across neighboring timesteps and camera angles, Hash3D substantially"},"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":"2404.06091","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T07:49:30Z","cross_cats_sorted":[],"title_canon_sha256":"87b1d0d491714dddf54f337cbe17e777ef200277ef013a97637e0f0e333455b7","abstract_canon_sha256":"a8903121a247102933a452a5e6f9dfce2d948e851de41a71902555d8878dc8a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:03.614032Z","signature_b64":"YszwzpDJnnqhk7Ar/DyHdJnEhgpi2AfiHx0qQ/DhmP4PP5anRXj57Ru+TrY/mGRelXxQ7rckU7wKvdHIlV6iBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49475aaee17b5d1cd7451acf1c1693a25d6ea79e2393aafb12224dd8d38d423a","last_reissued_at":"2026-07-05T08:06:03.613580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:03.613580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hash3D: Training-free Acceleration for 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinchao Wang, Xingyi Yang","submitted_at":"2024-04-09T07:49:30Z","abstract_excerpt":"The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se presents a critical hurdle to efficiency. In this paper, we introduce Hash3D, a universal acceleration for 3D generation without model training. Central to Hash3D is the insight that feature-map redundancy is prevalent in images rendered from camera positions and diffusion time-steps in close proximity. By effectively hashing and reusing these feature maps across neighboring timesteps and camera angles, Hash3D substantially"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06091","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/2404.06091/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":"2404.06091","created_at":"2026-07-05T08:06:03.613635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06091v1","created_at":"2026-07-05T08:06:03.613635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06091","created_at":"2026-07-05T08:06:03.613635+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFDVVLXBPNOR","created_at":"2026-07-05T08:06:03.613635+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFDVVLXBPNORZV2F","created_at":"2026-07-05T08:06:03.613635+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFDVVLXB","created_at":"2026-07-05T08:06:03.613635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":267,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ","json":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ.json","graph_json":"https://pith.science/api/pith-number/JFDVVLXBPNORZV2FDLHRYFUTUJ/graph.json","events_json":"https://pith.science/api/pith-number/JFDVVLXBPNORZV2FDLHRYFUTUJ/events.json","paper":"https://pith.science/paper/JFDVVLXB"},"agent_actions":{"view_html":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ","download_json":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ.json","view_paper":"https://pith.science/paper/JFDVVLXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06091&json=true","fetch_graph":"https://pith.science/api/pith-number/JFDVVLXBPNORZV2FDLHRYFUTUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JFDVVLXBPNORZV2FDLHRYFUTUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ/action/storage_attestation","attest_author":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ/action/author_attestation","sign_citation":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ/action/citation_signature","submit_replication":"https://pith.science/pith/JFDVVLXBPNORZV2FDLHRYFUTUJ/action/replication_record"}},"created_at":"2026-07-05T08:06:03.613635+00:00","updated_at":"2026-07-05T08:06:03.613635+00:00"}