{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RRQEXFBCYAAUWXV422GRJCVQJM","short_pith_number":"pith:RRQEXFBC","schema_version":"1.0","canonical_sha256":"8c604b9422c0014b5ebcd68d148ab04b14aa6847181c7d6951634c418ec2d911","source":{"kind":"arxiv","id":"2508.04078","version":1},"attestation_state":"computed","paper":{"title":"RLGS: Reinforcement Learning-Based Adaptive Hyperparameter Tuning for Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Changyang Li, Huangying Zhan, Qingan Yan, Yi Xu, Zhan Li","submitted_at":"2025-08-06T04:37:39Z","abstract_excerpt":"Hyperparameter tuning in 3D Gaussian Splatting (3DGS) is a labor-intensive and expert-driven process, often resulting in inconsistent reconstructions and suboptimal results. We propose RLGS, a plug-and-play reinforcement learning framework for adaptive hyperparameter tuning in 3DGS through lightweight policy modules, dynamically adjusting critical hyperparameters such as learning rates and densification thresholds. The framework is model-agnostic and seamlessly integrates into existing 3DGS pipelines without architectural modifications. We demonstrate its generalization ability across multiple"},"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":"2508.04078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-08-06T04:37:39Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"f611f1eec612ef6ce6d0e4db096ffbd0ec326d72e2bf37a113e2dec0dc7ba1fc","abstract_canon_sha256":"9f2348f458e813916ca703b8d81a22fae8bea90f118bed6119949df504e36501"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:20.309981Z","signature_b64":"OJS7LQv051HAivvzE3foLo4JCJwjJkKskHQsabKPATyUx/weKggMYMISrXgykMn1bw1+zy0EwXjZBUMGYNqZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c604b9422c0014b5ebcd68d148ab04b14aa6847181c7d6951634c418ec2d911","last_reissued_at":"2026-07-05T11:49:20.309542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:20.309542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLGS: Reinforcement Learning-Based Adaptive Hyperparameter Tuning for Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Changyang Li, Huangying Zhan, Qingan Yan, Yi Xu, Zhan Li","submitted_at":"2025-08-06T04:37:39Z","abstract_excerpt":"Hyperparameter tuning in 3D Gaussian Splatting (3DGS) is a labor-intensive and expert-driven process, often resulting in inconsistent reconstructions and suboptimal results. We propose RLGS, a plug-and-play reinforcement learning framework for adaptive hyperparameter tuning in 3DGS through lightweight policy modules, dynamically adjusting critical hyperparameters such as learning rates and densification thresholds. The framework is model-agnostic and seamlessly integrates into existing 3DGS pipelines without architectural modifications. We demonstrate its generalization ability across multiple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04078","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/2508.04078/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":"2508.04078","created_at":"2026-07-05T11:49:20.309598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04078v1","created_at":"2026-07-05T11:49:20.309598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04078","created_at":"2026-07-05T11:49:20.309598+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRQEXFBCYAAU","created_at":"2026-07-05T11:49:20.309598+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRQEXFBCYAAUWXV4","created_at":"2026-07-05T11:49:20.309598+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRQEXFBC","created_at":"2026-07-05T11:49:20.309598+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/RRQEXFBCYAAUWXV422GRJCVQJM","json":"https://pith.science/pith/RRQEXFBCYAAUWXV422GRJCVQJM.json","graph_json":"https://pith.science/api/pith-number/RRQEXFBCYAAUWXV422GRJCVQJM/graph.json","events_json":"https://pith.science/api/pith-number/RRQEXFBCYAAUWXV422GRJCVQJM/events.json","paper":"https://pith.science/paper/RRQEXFBC"},"agent_actions":{"view_html":"https://pith.science/pith/RRQEXFBCYAAUWXV422GRJCVQJM","download_json":"https://pith.science/pith/RRQEXFBCYAAUWXV422GRJCVQJM.json","view_paper":"https://pith.science/paper/RRQEXFBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04078&json=true","fetch_graph":"https://pith.science/api/pith-number/RRQEXFBCYAAUWXV422GRJCVQJM/graph.json","fetch_events":"https://pith.science/api/pith-number/RRQEXFBCYAAUWXV422GRJCVQJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRQEXFBCYAAUWXV422GRJCVQJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRQEXFBCYAAUWXV422GRJCVQJM/action/storage_attestation","attest_author":"https://pith.science/pith/RRQEXFBCYAAUWXV422GRJCVQJM/action/author_attestation","sign_citation":"https://pith.science/pith/RRQEXFBCYAAUWXV422GRJCVQJM/action/citation_signature","submit_replication":"https://pith.science/pith/RRQEXFBCYAAUWXV422GRJCVQJM/action/replication_record"}},"created_at":"2026-07-05T11:49:20.309598+00:00","updated_at":"2026-07-05T11:49:20.309598+00:00"}