{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GTWNZIJN5OFGNC6LNVENJKJ4MJ","short_pith_number":"pith:GTWNZIJN","schema_version":"1.0","canonical_sha256":"34ecdca12deb8a668bcb6d48d4a93c627cd76ab50095ce0b3dc8e1b6a4b97998","source":{"kind":"arxiv","id":"2407.10200","version":1},"attestation_state":"computed","paper":{"title":"Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ruijie Quan, Tuo Feng, Wenguan Wang, Yi Yang","submitted_at":"2024-07-14T13:42:05Z","abstract_excerpt":"Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this, existing pre-training strategies on shape data offer limited potential for 3D scene understanding due to significant disparities in point quantities. To tackle these challenges, we propose Shape2Scene (S2S), a novel method that learns representations of large-scale 3D scenes from 3D shape data. We first design multiscale and high-resolution backbones for shape an"},"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":"2407.10200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-14T13:42:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b8c6b255a9f6c41815aa44c283549bd88c23efd83e99b0d7341bf919abfe6a76","abstract_canon_sha256":"cf60ac4fc7c74091f5a7b027f5f26e03f1179c3fdb845bdc9dad928c9aa7c1ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:40.526468Z","signature_b64":"Kk21Mg/OnB3olR+MXG1n8W58XO4UgLEQFTwXDrGZU8uKPgzDu11HoMI4FPzSmLuiQiBxo3wRe2jYgRt8fmsHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34ecdca12deb8a668bcb6d48d4a93c627cd76ab50095ce0b3dc8e1b6a4b97998","last_reissued_at":"2026-07-05T08:43:40.526038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:40.526038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ruijie Quan, Tuo Feng, Wenguan Wang, Yi Yang","submitted_at":"2024-07-14T13:42:05Z","abstract_excerpt":"Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this, existing pre-training strategies on shape data offer limited potential for 3D scene understanding due to significant disparities in point quantities. To tackle these challenges, we propose Shape2Scene (S2S), a novel method that learns representations of large-scale 3D scenes from 3D shape data. We first design multiscale and high-resolution backbones for shape an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10200","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/2407.10200/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":"2407.10200","created_at":"2026-07-05T08:43:40.526095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10200v1","created_at":"2026-07-05T08:43:40.526095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10200","created_at":"2026-07-05T08:43:40.526095+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTWNZIJN5OFG","created_at":"2026-07-05T08:43:40.526095+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTWNZIJN5OFGNC6L","created_at":"2026-07-05T08:43:40.526095+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTWNZIJN","created_at":"2026-07-05T08:43:40.526095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20941","citing_title":"PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ","json":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ.json","graph_json":"https://pith.science/api/pith-number/GTWNZIJN5OFGNC6LNVENJKJ4MJ/graph.json","events_json":"https://pith.science/api/pith-number/GTWNZIJN5OFGNC6LNVENJKJ4MJ/events.json","paper":"https://pith.science/paper/GTWNZIJN"},"agent_actions":{"view_html":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ","download_json":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ.json","view_paper":"https://pith.science/paper/GTWNZIJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10200&json=true","fetch_graph":"https://pith.science/api/pith-number/GTWNZIJN5OFGNC6LNVENJKJ4MJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GTWNZIJN5OFGNC6LNVENJKJ4MJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ/action/storage_attestation","attest_author":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ/action/author_attestation","sign_citation":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ/action/citation_signature","submit_replication":"https://pith.science/pith/GTWNZIJN5OFGNC6LNVENJKJ4MJ/action/replication_record"}},"created_at":"2026-07-05T08:43:40.526095+00:00","updated_at":"2026-07-05T08:43:40.526095+00:00"}