{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FFK4NMUW6ROLHVGZSN6WKDKXGI","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":"7f295b02c578c7b232481415d4a06eaa3026e4822a4d9d8f555c6068f0cd6ecf","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T19:42:40Z","title_canon_sha256":"f19d11f472df839d62c936280dcc281dbece3138d0facbf56b7aa74b0411c809"},"schema_version":"1.0","source":{"id":"2112.02413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02413","created_at":"2026-07-05T03:37:52Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02413v1","created_at":"2026-07-05T03:37:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02413","created_at":"2026-07-05T03:37:52Z"},{"alias_kind":"pith_short_12","alias_value":"FFK4NMUW6ROL","created_at":"2026-07-05T03:37:52Z"},{"alias_kind":"pith_short_16","alias_value":"FFK4NMUW6ROLHVGZ","created_at":"2026-07-05T03:37:52Z"},{"alias_kind":"pith_short_8","alias_value":"FFK4NMUW","created_at":"2026-07-05T03:37:52Z"}],"graph_snapshots":[{"event_id":"sha256:9496ed9ca6d3120fa8f0b95ea5cb6f0c799ef31e6b2b8854e7a0a7409707d03c","target":"graph","created_at":"2026-07-05T03:37:52Z","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/2112.02413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in open-vocabulary settings. However, it remains under explored that whether CLIP, pre-trained by large-scale image-text pairs in 2D, can be generalized to 3D recognition. In this paper, we identify such a setting is feasible by proposing PointCLIP, which conducts alignment between CLIP-encoded point cloud and 3D category texts. Specifically, we encode a point cloud by projecting ","authors_text":"Bin Cui, Hongsheng Li, Kunchang Li, Peng Gao, Renrui Zhang, Wei Zhang, Xupeng Miao, Yu Qiao, Ziyu Guo","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T19:42:40Z","title":"PointCLIP: Point Cloud Understanding by CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02413","kind":"arxiv","version":1},"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":"sha256:26e51302d19d5d3243ef6441c9e7faeaf3a89bc4232abc08a93410dc29ff12ff","target":"record","created_at":"2026-07-05T03:37:52Z","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":"7f295b02c578c7b232481415d4a06eaa3026e4822a4d9d8f555c6068f0cd6ecf","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T19:42:40Z","title_canon_sha256":"f19d11f472df839d62c936280dcc281dbece3138d0facbf56b7aa74b0411c809"},"schema_version":"1.0","source":{"id":"2112.02413","kind":"arxiv","version":1}},"canonical_sha256":"2955c6b296f45cb3d4d9937d650d57321c27229a3f61bd3a91330ef038b9d181","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2955c6b296f45cb3d4d9937d650d57321c27229a3f61bd3a91330ef038b9d181","first_computed_at":"2026-07-05T03:37:52.527347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:52.527347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YNCa/L9mO+PR6OOu/igPK0XkGAtwtLiFi8sdqKAAsK5EpxlaELJPG6P0761IOoi1z5GiR3Nc9h20asoV6eDPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:52.527819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26e51302d19d5d3243ef6441c9e7faeaf3a89bc4232abc08a93410dc29ff12ff","sha256:9496ed9ca6d3120fa8f0b95ea5cb6f0c799ef31e6b2b8854e7a0a7409707d03c"],"state_sha256":"cf5c766f2ba79e20f252129f6f4999631130385bc59dfb7fe3b08dd7ab9cc540"}