{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YN65ZRKX4UGDFUH2MGAVIRHZ7C","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":"5b9afaa0d0cb4023845700dac81c375ba9e6877f457af1c7eaeb4090aed87dc6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-10T01:34:47Z","title_canon_sha256":"206be2902ff85a7baeffc40d7a1b61d579e43ff7e5a51357682941fbbaf25146"},"schema_version":"1.0","source":{"id":"2212.05171","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05171","created_at":"2026-07-05T06:19:54Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05171v4","created_at":"2026-07-05T06:19:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05171","created_at":"2026-07-05T06:19:54Z"},{"alias_kind":"pith_short_12","alias_value":"YN65ZRKX4UGD","created_at":"2026-07-05T06:19:54Z"},{"alias_kind":"pith_short_16","alias_value":"YN65ZRKX4UGDFUH2","created_at":"2026-07-05T06:19:54Z"},{"alias_kind":"pith_short_8","alias_value":"YN65ZRKX","created_at":"2026-07-05T06:19:54Z"}],"graph_snapshots":[{"event_id":"sha256:c05be9d145af66dceeb6a4f5695630a7d913414e8f26ba1b7da73bf65411d20e","target":"graph","created_at":"2026-07-05T06:19:54Z","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/2212.05171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recognition capabilities of current state-of-the-art 3D models are limited by datasets with a small number of annotated data and a pre-defined set of categories. In its 2D counterpart, recent advances have shown that similar problems can be significantly alleviated by employing knowledge from other modalities, such as language. Inspired by this, leveraging multimodal information for 3D modality could be promising to improve 3D understanding under the restricted data regime, but this line of research is not well studied. Therefore, we introduce ULIP to learn a unified representation of imag","authors_text":"Caiming Xiong, Chen Xing, Jiajun Wu, Juan Carlos Niebles, Le Xue, Mingfei Gao, Ran Xu, Roberto Mart\\'in-Mart\\'in, Silvio Savarese","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-10T01:34:47Z","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05171","kind":"arxiv","version":4},"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":"sha256:12fdb0ebb84c5dced27b036e840fd9c7fee960a1e8e7a55892aaa43cb42f6392","target":"record","created_at":"2026-07-05T06:19:54Z","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":"5b9afaa0d0cb4023845700dac81c375ba9e6877f457af1c7eaeb4090aed87dc6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-10T01:34:47Z","title_canon_sha256":"206be2902ff85a7baeffc40d7a1b61d579e43ff7e5a51357682941fbbaf25146"},"schema_version":"1.0","source":{"id":"2212.05171","kind":"arxiv","version":4}},"canonical_sha256":"c37ddcc557e50c32d0fa61815444f9f8977b08b385d321094e95de15cc52a21c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c37ddcc557e50c32d0fa61815444f9f8977b08b385d321094e95de15cc52a21c","first_computed_at":"2026-07-05T06:19:54.496897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:54.496897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A+oeejCcXG+nIdFclfe6cuP8wxKq/qteuH4d3YkQEnO2X5RGZ7pRSfl1fW+3T9ESTQUdED4wusopj2rHAyDtDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:54.497353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.05171","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12fdb0ebb84c5dced27b036e840fd9c7fee960a1e8e7a55892aaa43cb42f6392","sha256:c05be9d145af66dceeb6a4f5695630a7d913414e8f26ba1b7da73bf65411d20e"],"state_sha256":"24d3896e593bc26b2ada59e998aafcf862b930e987f7dcb132eedced1e8d644b"}