{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:66GHFDGGUIJHPJDW4Z7ZHM25BX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"91072581bdbad80b104ffcec37871e42d097de620c372d0dc51f4fe4fc008348","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T17:52:24Z","title_canon_sha256":"2d142fabc26433750a771449293ae0d46277a10e4962a4767b66cc084046a318"},"schema_version":"1.0","source":{"id":"2303.11313","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11313","created_at":"2026-07-05T06:02:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11313v3","created_at":"2026-07-05T06:02:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11313","created_at":"2026-07-05T06:02:33Z"},{"alias_kind":"pith_short_12","alias_value":"66GHFDGGUIJH","created_at":"2026-07-05T06:02:33Z"},{"alias_kind":"pith_short_16","alias_value":"66GHFDGGUIJHPJDW","created_at":"2026-07-05T06:02:33Z"},{"alias_kind":"pith_short_8","alias_value":"66GHFDGG","created_at":"2026-07-05T06:02:33Z"}],"graph_snapshots":[{"event_id":"sha256:91c80d62f3839f7ea2587d439e689cd0cce5de342d2e83eabd88962b70ef0a90","target":"graph","created_at":"2026-07-05T06:02:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.11313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language models like CLIP have been widely adopted for various tasks due to their impressive zero-shot capabilities. However, CLIP is not suitable for extracting 3D geometric features as it was trained on only images and text by natural language supervision. We work on addressing this limitation and propose a new framework termed CG3D (CLIP Goes 3D) where a 3D encoder is learned to exhibit zero-shot capabilities. CG3D is trained using triplets of pointclouds, corresponding rendered 2D images, and texts using natural language supervision. To align the features in a multimodal embedding s","authors_text":"Deepti Hegde, Jeya Maria Jose Valanarasu, Vishal M. Patel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T17:52:24Z","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11313","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7e92495a53eec720ae6978d8c0b0a09e83906b6a1aca09d2e0d7a2b903e83241","target":"record","created_at":"2026-07-05T06:02:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"91072581bdbad80b104ffcec37871e42d097de620c372d0dc51f4fe4fc008348","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T17:52:24Z","title_canon_sha256":"2d142fabc26433750a771449293ae0d46277a10e4962a4767b66cc084046a318"},"schema_version":"1.0","source":{"id":"2303.11313","kind":"arxiv","version":3}},"canonical_sha256":"f78c728cc6a21277a476e67f93b35d0dcf8635f6b0345c1b6dc9f679abd86ab6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f78c728cc6a21277a476e67f93b35d0dcf8635f6b0345c1b6dc9f679abd86ab6","first_computed_at":"2026-07-05T06:02:33.334629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:33.334629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fQt7m38IDrrwgERA9OFcsadsBw5g6HOTnmuSoopQx6uJffftWRAPXkqodx2tl6tH206vS0V/ln2EExt2YcHOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:33.335049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.11313","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e92495a53eec720ae6978d8c0b0a09e83906b6a1aca09d2e0d7a2b903e83241","sha256:91c80d62f3839f7ea2587d439e689cd0cce5de342d2e83eabd88962b70ef0a90"],"state_sha256":"b0de1204d3dc7af682a56be39b4a114a7f82fd332c32b30e4963c532d5c14067"}