{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AQA3UWK7PM6V6ARSAMBQMTUM3A","short_pith_number":"pith:AQA3UWK7","schema_version":"1.0","canonical_sha256":"0401ba595f7b3d5f02320303064e8cd82f05376ad52007b34839778ec301b3a0","source":{"kind":"arxiv","id":"2505.20473","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Preconditioning for Neural Field Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Alec Jacobson, Merlin Nimier-David, Nicholas Sharp, Selena Ling","submitted_at":"2025-05-26T19:13:41Z","abstract_excerpt":"Neural fields are a highly effective representation across visual computing. This work observes that fitting these fields is greatly improved by incorporating spatial stochasticity during training, and that this simple technique can replace or even outperform custom-designed hierarchies and frequency space constructions. The approach is formalized as implicitly operating on a blurred version of the field, evaluated in-expectation by sampling with Gaussian-distributed offsets. Querying the blurred field during optimization greatly improves convergence and robustness, akin to the role of precond"},"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":"2505.20473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-05-26T19:13:41Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"073b9621c8dd062d840223a514f2eebf64dc6d9e51c268f2fe0c6674c2f93bda","abstract_canon_sha256":"91c0b67012ee611b013352adc6308a2b8fe60a10145c942e58d6d538791e041a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:12.994889Z","signature_b64":"1w++FDfj+EGIjabpg6ns7xBJbEgkNgBXxz1IZ/ZAPT/4UsJ6ksAhXB3JLaahxpgZItW1U4zHozdLlz0MtpeoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0401ba595f7b3d5f02320303064e8cd82f05376ad52007b34839778ec301b3a0","last_reissued_at":"2026-07-05T11:10:12.994368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:12.994368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Preconditioning for Neural Field Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Alec Jacobson, Merlin Nimier-David, Nicholas Sharp, Selena Ling","submitted_at":"2025-05-26T19:13:41Z","abstract_excerpt":"Neural fields are a highly effective representation across visual computing. This work observes that fitting these fields is greatly improved by incorporating spatial stochasticity during training, and that this simple technique can replace or even outperform custom-designed hierarchies and frequency space constructions. The approach is formalized as implicitly operating on a blurred version of the field, evaluated in-expectation by sampling with Gaussian-distributed offsets. Querying the blurred field during optimization greatly improves convergence and robustness, akin to the role of precond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20473","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/2505.20473/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":"2505.20473","created_at":"2026-07-05T11:10:12.994439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20473v1","created_at":"2026-07-05T11:10:12.994439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20473","created_at":"2026-07-05T11:10:12.994439+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQA3UWK7PM6V","created_at":"2026-07-05T11:10:12.994439+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQA3UWK7PM6V6ARS","created_at":"2026-07-05T11:10:12.994439+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQA3UWK7","created_at":"2026-07-05T11:10:12.994439+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/AQA3UWK7PM6V6ARSAMBQMTUM3A","json":"https://pith.science/pith/AQA3UWK7PM6V6ARSAMBQMTUM3A.json","graph_json":"https://pith.science/api/pith-number/AQA3UWK7PM6V6ARSAMBQMTUM3A/graph.json","events_json":"https://pith.science/api/pith-number/AQA3UWK7PM6V6ARSAMBQMTUM3A/events.json","paper":"https://pith.science/paper/AQA3UWK7"},"agent_actions":{"view_html":"https://pith.science/pith/AQA3UWK7PM6V6ARSAMBQMTUM3A","download_json":"https://pith.science/pith/AQA3UWK7PM6V6ARSAMBQMTUM3A.json","view_paper":"https://pith.science/paper/AQA3UWK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20473&json=true","fetch_graph":"https://pith.science/api/pith-number/AQA3UWK7PM6V6ARSAMBQMTUM3A/graph.json","fetch_events":"https://pith.science/api/pith-number/AQA3UWK7PM6V6ARSAMBQMTUM3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQA3UWK7PM6V6ARSAMBQMTUM3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQA3UWK7PM6V6ARSAMBQMTUM3A/action/storage_attestation","attest_author":"https://pith.science/pith/AQA3UWK7PM6V6ARSAMBQMTUM3A/action/author_attestation","sign_citation":"https://pith.science/pith/AQA3UWK7PM6V6ARSAMBQMTUM3A/action/citation_signature","submit_replication":"https://pith.science/pith/AQA3UWK7PM6V6ARSAMBQMTUM3A/action/replication_record"}},"created_at":"2026-07-05T11:10:12.994439+00:00","updated_at":"2026-07-05T11:10:12.994439+00:00"}