{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RHZ4A4XBLZPQDYQVYW3XZ237G4","short_pith_number":"pith:RHZ4A4XB","schema_version":"1.0","canonical_sha256":"89f3c072e15e5f01e215c5b77ceb7f373c6545541bff117681a85a6dcc29e66d","source":{"kind":"arxiv","id":"2506.08777","version":2},"attestation_state":"computed","paper":{"title":"Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ben Fei, Keyi Liu, Weidong Yang, Ying He","submitted_at":"2025-06-10T13:19:21Z","abstract_excerpt":"Self-supervised learning (SSL) for point cloud pre-training has become a cornerstone for many 3D vision tasks, enabling effective learning from large-scale unannotated data. At the scene level, existing SSL methods often incorporate volume rendering into the pre-training framework, using RGB-D images as reconstruction signals to facilitate cross-modal learning. This strategy promotes alignment between 2D and 3D modalities and enables the model to benefit from rich visual cues in the RGB-D inputs. However, these approaches are limited by their reliance on implicit scene representations and high"},"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":"2506.08777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T13:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"5c33d4cde9f682052f1715fe19a699b96d09e583ca17fb78bc3525482733252e","abstract_canon_sha256":"b4fa35c8466bb820857bba796cedc967dc2dc15152db3bfeaab82dc766d7812f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:30.120816Z","signature_b64":"vSJOgaOAU9ND8nks91bJe5pPiDsF3KT7vW4qe3QLDA/Z1vRdoNnUqKMZtkpJBcJAxfm2cQKSI3QQvdRJ+qQrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89f3c072e15e5f01e215c5b77ceb7f373c6545541bff117681a85a6dcc29e66d","last_reissued_at":"2026-07-05T11:19:30.120384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:30.120384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ben Fei, Keyi Liu, Weidong Yang, Ying He","submitted_at":"2025-06-10T13:19:21Z","abstract_excerpt":"Self-supervised learning (SSL) for point cloud pre-training has become a cornerstone for many 3D vision tasks, enabling effective learning from large-scale unannotated data. At the scene level, existing SSL methods often incorporate volume rendering into the pre-training framework, using RGB-D images as reconstruction signals to facilitate cross-modal learning. This strategy promotes alignment between 2D and 3D modalities and enables the model to benefit from rich visual cues in the RGB-D inputs. However, these approaches are limited by their reliance on implicit scene representations and high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08777","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/2506.08777/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":"2506.08777","created_at":"2026-07-05T11:19:30.120444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08777v2","created_at":"2026-07-05T11:19:30.120444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08777","created_at":"2026-07-05T11:19:30.120444+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHZ4A4XBLZPQ","created_at":"2026-07-05T11:19:30.120444+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHZ4A4XBLZPQDYQV","created_at":"2026-07-05T11:19:30.120444+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHZ4A4XB","created_at":"2026-07-05T11:19:30.120444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17533","citing_title":"Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4","json":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4.json","graph_json":"https://pith.science/api/pith-number/RHZ4A4XBLZPQDYQVYW3XZ237G4/graph.json","events_json":"https://pith.science/api/pith-number/RHZ4A4XBLZPQDYQVYW3XZ237G4/events.json","paper":"https://pith.science/paper/RHZ4A4XB"},"agent_actions":{"view_html":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4","download_json":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4.json","view_paper":"https://pith.science/paper/RHZ4A4XB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08777&json=true","fetch_graph":"https://pith.science/api/pith-number/RHZ4A4XBLZPQDYQVYW3XZ237G4/graph.json","fetch_events":"https://pith.science/api/pith-number/RHZ4A4XBLZPQDYQVYW3XZ237G4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4/action/storage_attestation","attest_author":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4/action/author_attestation","sign_citation":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4/action/citation_signature","submit_replication":"https://pith.science/pith/RHZ4A4XBLZPQDYQVYW3XZ237G4/action/replication_record"}},"created_at":"2026-07-05T11:19:30.120444+00:00","updated_at":"2026-07-05T11:19:30.120444+00:00"}