{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CM5A73IDUWP5YRDXZ6V5L63RJM","short_pith_number":"pith:CM5A73ID","schema_version":"1.0","canonical_sha256":"133a0fed03a59fdc4477cfabd5fb714b1e72076a51cc43f6b02725f06678fedb","source":{"kind":"arxiv","id":"2605.29549","version":1},"attestation_state":"computed","paper":{"title":"Learning Representations from 3D Gaussian Splats","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arkadiusz Gawe{\\l}, Halina Kwa\\'snicka, Julia Farganus, Krzysztof \\.Zurawicki, Weronika Jakubowska","submitted_at":"2026-05-28T08:02:17Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluation of various geometric deep learning architectures for the classification of 3D scenes represented using Gaussian Splatting. We benchmark point-based and graph-based models across both traditional point cloud datasets and dedicated Gaussian Splatting datasets. Scenes are embedded into latent representations, which are evaluated through end-to-end classification, l"},"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":"2605.29549","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:02:17Z","cross_cats_sorted":[],"title_canon_sha256":"25eb0362693d7dede1d7e019bd2b93aa7810cb49912e9596a9d76d89ec32abd3","abstract_canon_sha256":"73271b83439e00e283f74767393509cee1fb3b918343724e58057d4d33e351d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:46.600419Z","signature_b64":"NgP8CvKssmIvmrkWVC9w3oBfQ3sp15j0AL8gMk9XQls7MZcNVZJlfdCwVxn5D0xmGTfwTqi1lUIUseTBT+FxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"133a0fed03a59fdc4477cfabd5fb714b1e72076a51cc43f6b02725f06678fedb","last_reissued_at":"2026-05-29T01:05:46.599041Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:46.599041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Representations from 3D Gaussian Splats","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arkadiusz Gawe{\\l}, Halina Kwa\\'snicka, Julia Farganus, Krzysztof \\.Zurawicki, Weronika Jakubowska","submitted_at":"2026-05-28T08:02:17Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluation of various geometric deep learning architectures for the classification of 3D scenes represented using Gaussian Splatting. We benchmark point-based and graph-based models across both traditional point cloud datasets and dedicated Gaussian Splatting datasets. Scenes are embedded into latent representations, which are evaluated through end-to-end classification, l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29549","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/2605.29549/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":"2605.29549","created_at":"2026-05-29T01:05:46.599160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29549v1","created_at":"2026-05-29T01:05:46.599160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29549","created_at":"2026-05-29T01:05:46.599160+00:00"},{"alias_kind":"pith_short_12","alias_value":"CM5A73IDUWP5","created_at":"2026-05-29T01:05:46.599160+00:00"},{"alias_kind":"pith_short_16","alias_value":"CM5A73IDUWP5YRDX","created_at":"2026-05-29T01:05:46.599160+00:00"},{"alias_kind":"pith_short_8","alias_value":"CM5A73ID","created_at":"2026-05-29T01:05:46.599160+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/CM5A73IDUWP5YRDXZ6V5L63RJM","json":"https://pith.science/pith/CM5A73IDUWP5YRDXZ6V5L63RJM.json","graph_json":"https://pith.science/api/pith-number/CM5A73IDUWP5YRDXZ6V5L63RJM/graph.json","events_json":"https://pith.science/api/pith-number/CM5A73IDUWP5YRDXZ6V5L63RJM/events.json","paper":"https://pith.science/paper/CM5A73ID"},"agent_actions":{"view_html":"https://pith.science/pith/CM5A73IDUWP5YRDXZ6V5L63RJM","download_json":"https://pith.science/pith/CM5A73IDUWP5YRDXZ6V5L63RJM.json","view_paper":"https://pith.science/paper/CM5A73ID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29549&json=true","fetch_graph":"https://pith.science/api/pith-number/CM5A73IDUWP5YRDXZ6V5L63RJM/graph.json","fetch_events":"https://pith.science/api/pith-number/CM5A73IDUWP5YRDXZ6V5L63RJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CM5A73IDUWP5YRDXZ6V5L63RJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CM5A73IDUWP5YRDXZ6V5L63RJM/action/storage_attestation","attest_author":"https://pith.science/pith/CM5A73IDUWP5YRDXZ6V5L63RJM/action/author_attestation","sign_citation":"https://pith.science/pith/CM5A73IDUWP5YRDXZ6V5L63RJM/action/citation_signature","submit_replication":"https://pith.science/pith/CM5A73IDUWP5YRDXZ6V5L63RJM/action/replication_record"}},"created_at":"2026-05-29T01:05:46.599160+00:00","updated_at":"2026-05-29T01:05:46.599160+00:00"}