{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2XW44G3QSI6CYGKYDUDTJUEFSU","short_pith_number":"pith:2XW44G3Q","schema_version":"1.0","canonical_sha256":"d5edce1b70923c2c19581d0734d0859505e87dde5eee2bb472520f58f8df77ab","source":{"kind":"arxiv","id":"2306.02329","version":1},"attestation_state":"computed","paper":{"title":"Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Delitzas, Georgios Vlassis, Gregor Bachmann, Maria Parelli, Nikolas Hars, Sotirios Anagnostidis, Thomas Hofmann","submitted_at":"2023-06-04T11:08:53Z","abstract_excerpt":"Training models to apply common-sense linguistic knowledge and visual concepts from 2D images to 3D scene understanding is a promising direction that researchers have only recently started to explore. However, it still remains understudied whether 2D distilled knowledge can provide useful representations for downstream 3D vision-language tasks such as 3D question answering. In this paper, we propose a novel 3D pre-training Vision-Language method, namely Multi-CLIP, that enables a model to learn language-grounded and transferable 3D scene point cloud representations. We leverage the representat"},"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":"2306.02329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-04T11:08:53Z","cross_cats_sorted":[],"title_canon_sha256":"c281d351d6c26fc1901a0834294618ac548d97fc6c2c6d41ae1e206e09787143","abstract_canon_sha256":"ba0653aa09f19575af8e4d48c2f37d62eac94c243d1783f6f459f8571e0d2868"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:05.095209Z","signature_b64":"+KSCSBbHMT7G7mwUhtkb55KZQ7EVOYT9UDTNTTXiuhIubgA67s/eCyQPNj11qnAuj+gKFNqCnjcbe1kS6ZDADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5edce1b70923c2c19581d0734d0859505e87dde5eee2bb472520f58f8df77ab","last_reissued_at":"2026-07-05T06:19:05.094810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:05.094810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Delitzas, Georgios Vlassis, Gregor Bachmann, Maria Parelli, Nikolas Hars, Sotirios Anagnostidis, Thomas Hofmann","submitted_at":"2023-06-04T11:08:53Z","abstract_excerpt":"Training models to apply common-sense linguistic knowledge and visual concepts from 2D images to 3D scene understanding is a promising direction that researchers have only recently started to explore. However, it still remains understudied whether 2D distilled knowledge can provide useful representations for downstream 3D vision-language tasks such as 3D question answering. In this paper, we propose a novel 3D pre-training Vision-Language method, namely Multi-CLIP, that enables a model to learn language-grounded and transferable 3D scene point cloud representations. We leverage the representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02329","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/2306.02329/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":"2306.02329","created_at":"2026-07-05T06:19:05.094865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02329v1","created_at":"2026-07-05T06:19:05.094865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02329","created_at":"2026-07-05T06:19:05.094865+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XW44G3QSI6C","created_at":"2026-07-05T06:19:05.094865+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XW44G3QSI6CYGKY","created_at":"2026-07-05T06:19:05.094865+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XW44G3Q","created_at":"2026-07-05T06:19:05.094865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07001","citing_title":"Ego-Human Motion Prediction with 3D-Aware LLM","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU","json":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU.json","graph_json":"https://pith.science/api/pith-number/2XW44G3QSI6CYGKYDUDTJUEFSU/graph.json","events_json":"https://pith.science/api/pith-number/2XW44G3QSI6CYGKYDUDTJUEFSU/events.json","paper":"https://pith.science/paper/2XW44G3Q"},"agent_actions":{"view_html":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU","download_json":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU.json","view_paper":"https://pith.science/paper/2XW44G3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02329&json=true","fetch_graph":"https://pith.science/api/pith-number/2XW44G3QSI6CYGKYDUDTJUEFSU/graph.json","fetch_events":"https://pith.science/api/pith-number/2XW44G3QSI6CYGKYDUDTJUEFSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/action/storage_attestation","attest_author":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/action/author_attestation","sign_citation":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/action/citation_signature","submit_replication":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/action/replication_record"}},"created_at":"2026-07-05T06:19:05.094865+00:00","updated_at":"2026-07-05T06:19:05.094865+00:00"}