{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XVQO5QS5AS7L4ILHR7R4EMAAVY","short_pith_number":"pith:XVQO5QS5","schema_version":"1.0","canonical_sha256":"bd60eec25d04bebe21678fe3c23000ae181bcc513c7e3c2e0bc07f02771e3629","source":{"kind":"arxiv","id":"2501.13975","version":2},"attestation_state":"computed","paper":{"title":"3DGS$^2$: Near Second-order Converging 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chenfanfu Jiang, Lei Lan, Tianjia Shao, Yin Yang, Yu Zhang, Zixuan Lu","submitted_at":"2025-01-22T22:28:11Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as a mainstream solution for novel view synthesis and 3D reconstruction. By explicitly encoding a 3D scene using a collection of Gaussian kernels, 3DGS achieves high-quality rendering with superior efficiency. As a learning-based approach, 3DGS training has been dealt with the standard stochastic gradient descent (SGD) method, which offers at most linear convergence. Consequently, training often requires tens of minutes, even with GPU acceleration. This paper introduces a (near) second-order convergent training algorithm for 3DGS, leveraging its unique "},"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":"2501.13975","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-22T22:28:11Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"4c5e150401cef835bee6b318e7884e9eca46f583cc051cb14a45a27a4b2a6dd3","abstract_canon_sha256":"2d7817ab2b3b59950084a2cd867610d94503ce76c1384b238bc03741f54941a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:48.742527Z","signature_b64":"3Cr4/1m7sHNYYdiliUrVRU9ZOInFpNaap4Shz38064LWOTAJ7UDkSeIT2GsD1PQP9AUC4SbzJlF5Vp6rGipBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd60eec25d04bebe21678fe3c23000ae181bcc513c7e3c2e0bc07f02771e3629","last_reissued_at":"2026-07-05T10:05:48.742000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:48.742000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3DGS$^2$: Near Second-order Converging 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chenfanfu Jiang, Lei Lan, Tianjia Shao, Yin Yang, Yu Zhang, Zixuan Lu","submitted_at":"2025-01-22T22:28:11Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as a mainstream solution for novel view synthesis and 3D reconstruction. By explicitly encoding a 3D scene using a collection of Gaussian kernels, 3DGS achieves high-quality rendering with superior efficiency. As a learning-based approach, 3DGS training has been dealt with the standard stochastic gradient descent (SGD) method, which offers at most linear convergence. Consequently, training often requires tens of minutes, even with GPU acceleration. This paper introduces a (near) second-order convergent training algorithm for 3DGS, leveraging its unique "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13975","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/2501.13975/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":"2501.13975","created_at":"2026-07-05T10:05:48.742066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13975v2","created_at":"2026-07-05T10:05:48.742066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13975","created_at":"2026-07-05T10:05:48.742066+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVQO5QS5AS7L","created_at":"2026-07-05T10:05:48.742066+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVQO5QS5AS7L4ILH","created_at":"2026-07-05T10:05:48.742066+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVQO5QS5","created_at":"2026-07-05T10:05:48.742066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03775","citing_title":"ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY","json":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY.json","graph_json":"https://pith.science/api/pith-number/XVQO5QS5AS7L4ILHR7R4EMAAVY/graph.json","events_json":"https://pith.science/api/pith-number/XVQO5QS5AS7L4ILHR7R4EMAAVY/events.json","paper":"https://pith.science/paper/XVQO5QS5"},"agent_actions":{"view_html":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY","download_json":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY.json","view_paper":"https://pith.science/paper/XVQO5QS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13975&json=true","fetch_graph":"https://pith.science/api/pith-number/XVQO5QS5AS7L4ILHR7R4EMAAVY/graph.json","fetch_events":"https://pith.science/api/pith-number/XVQO5QS5AS7L4ILHR7R4EMAAVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY/action/storage_attestation","attest_author":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY/action/author_attestation","sign_citation":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY/action/citation_signature","submit_replication":"https://pith.science/pith/XVQO5QS5AS7L4ILHR7R4EMAAVY/action/replication_record"}},"created_at":"2026-07-05T10:05:48.742066+00:00","updated_at":"2026-07-05T10:05:48.742066+00:00"}