{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R46S4BPNQCCDLNJMQWXTEK5QGE","short_pith_number":"pith:R46S4BPN","schema_version":"1.0","canonical_sha256":"8f3d2e05ed808435b52c85af322bb03103ec1f15804a7f8a775f83bc2e674a33","source":{"kind":"arxiv","id":"2605.15760","version":1},"attestation_state":"computed","paper":{"title":"Learn2Splat: Extending the Horizon of Learned 3DGS Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Peleg, Andreas Geiger, Gerard Pons-Moll, Haofei Xu, Lorenzo Porzi, Naama Pearl, Patricia Gschossmann, Peter Kontschieder, Stefano Esposito","submitted_at":"2026-05-15T09:21:29Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) optimization is most commonly performed using standard optimizers (Adam, SGD). While stable across diverse scenes, standard optimizers are general-purpose and not tailored to the structure of the problem. In particular, they produce independent parameter updates that do not capture the structural and spatial relationships within a scene, leading to inefficient optimization and slow convergence. Recent works introduced learned optimizers that predict correlated updates informed by inter-parameter and inter-Gaussian dependencies. However, these methods are trained fo"},"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":"2605.15760","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T09:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"d6941dbe3be208387f71e475464fe720afaf91479bb2b3ff23e65a3b9cd0e910","abstract_canon_sha256":"c63c827b9f617585b71f94665d0afd07c4a7ddf479c30fc34a611f26def22234"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:16.788786Z","signature_b64":"kBiZEiUrXl8uUchlXQnOvgAoGfna7UDq3xubC6jOFd13Zk3jynGFOctSPNrPzfE5z4NbQZfCIR7zgUIM2cdWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f3d2e05ed808435b52c85af322bb03103ec1f15804a7f8a775f83bc2e674a33","last_reissued_at":"2026-05-20T00:01:16.787907Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:16.787907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn2Splat: Extending the Horizon of Learned 3DGS Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Peleg, Andreas Geiger, Gerard Pons-Moll, Haofei Xu, Lorenzo Porzi, Naama Pearl, Patricia Gschossmann, Peter Kontschieder, Stefano Esposito","submitted_at":"2026-05-15T09:21:29Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) optimization is most commonly performed using standard optimizers (Adam, SGD). While stable across diverse scenes, standard optimizers are general-purpose and not tailored to the structure of the problem. In particular, they produce independent parameter updates that do not capture the structural and spatial relationships within a scene, leading to inefficient optimization and slow convergence. Recent works introduced learned optimizers that predict correlated updates informed by inter-parameter and inter-Gaussian dependencies. However, these methods are trained fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15760","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/2605.15760/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.764037Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.956705Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2ff877e10c418129c67b835bc27caf4a1a35c4f65805e4ccbb0bb25d91bdb39b"},"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":"2605.15760","created_at":"2026-05-20T00:01:16.788043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15760v1","created_at":"2026-05-20T00:01:16.788043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15760","created_at":"2026-05-20T00:01:16.788043+00:00"},{"alias_kind":"pith_short_12","alias_value":"R46S4BPNQCCD","created_at":"2026-05-20T00:01:16.788043+00:00"},{"alias_kind":"pith_short_16","alias_value":"R46S4BPNQCCDLNJM","created_at":"2026-05-20T00:01:16.788043+00:00"},{"alias_kind":"pith_short_8","alias_value":"R46S4BPN","created_at":"2026-05-20T00:01:16.788043+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/R46S4BPNQCCDLNJMQWXTEK5QGE","json":"https://pith.science/pith/R46S4BPNQCCDLNJMQWXTEK5QGE.json","graph_json":"https://pith.science/api/pith-number/R46S4BPNQCCDLNJMQWXTEK5QGE/graph.json","events_json":"https://pith.science/api/pith-number/R46S4BPNQCCDLNJMQWXTEK5QGE/events.json","paper":"https://pith.science/paper/R46S4BPN"},"agent_actions":{"view_html":"https://pith.science/pith/R46S4BPNQCCDLNJMQWXTEK5QGE","download_json":"https://pith.science/pith/R46S4BPNQCCDLNJMQWXTEK5QGE.json","view_paper":"https://pith.science/paper/R46S4BPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15760&json=true","fetch_graph":"https://pith.science/api/pith-number/R46S4BPNQCCDLNJMQWXTEK5QGE/graph.json","fetch_events":"https://pith.science/api/pith-number/R46S4BPNQCCDLNJMQWXTEK5QGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R46S4BPNQCCDLNJMQWXTEK5QGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R46S4BPNQCCDLNJMQWXTEK5QGE/action/storage_attestation","attest_author":"https://pith.science/pith/R46S4BPNQCCDLNJMQWXTEK5QGE/action/author_attestation","sign_citation":"https://pith.science/pith/R46S4BPNQCCDLNJMQWXTEK5QGE/action/citation_signature","submit_replication":"https://pith.science/pith/R46S4BPNQCCDLNJMQWXTEK5QGE/action/replication_record"}},"created_at":"2026-05-20T00:01:16.788043+00:00","updated_at":"2026-05-20T00:01:16.788043+00:00"}