{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WKWLXYDABLEITX7WX62WNAQX5Z","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":"b0a37d8414b89a57ae67b388b1b6b2c8356de93368ab9685f0d33348271644dc","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T17:54:49Z","title_canon_sha256":"d6bcdbe2de57f33c6a570ea7b92f1bbea942f6ba3a10b2fc074d0fb6c687cd04"},"schema_version":"1.0","source":{"id":"2404.11605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11605","created_at":"2026-07-05T08:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11605v1","created_at":"2026-07-05T08:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11605","created_at":"2026-07-05T08:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"WKWLXYDABLEI","created_at":"2026-07-05T08:09:10Z"},{"alias_kind":"pith_short_16","alias_value":"WKWLXYDABLEITX7W","created_at":"2026-07-05T08:09:10Z"},{"alias_kind":"pith_short_8","alias_value":"WKWLXYDA","created_at":"2026-07-05T08:09:10Z"}],"graph_snapshots":[{"event_id":"sha256:a3d8ea641b25cdb712ee6207f3554da1b8073398c6a3d77409bfcc536843ab25","target":"graph","created_at":"2026-07-05T08:09:10Z","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/2404.11605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the real world through point cloud video is a crucial aspect of robotics and autonomous driving systems. However, prevailing methods for 4D point cloud recognition have limitations due to sensor resolution, which leads to a lack of detailed information. Recent advances have shown that Vision-Language Models (VLM) pre-trained on web-scale text-image datasets can learn fine-grained visual concepts that can be transferred to various downstream tasks. However, effectively integrating VLM into the domain of 4D point clouds remains an unresolved problem. In this work, we propose the Vi","authors_text":"Mengyuan Liu, Shen Zhao, Xia Li, Xiangtai Li, Yunhai Tong, Zhichao Deng","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T17:54:49Z","title":"VG4D: Vision-Language Model Goes 4D Video Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11605","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:c3784805d5fd0c8f7c17356245acec893f6995be330c6258457d346e4c6acd37","target":"record","created_at":"2026-07-05T08:09:10Z","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":"b0a37d8414b89a57ae67b388b1b6b2c8356de93368ab9685f0d33348271644dc","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T17:54:49Z","title_canon_sha256":"d6bcdbe2de57f33c6a570ea7b92f1bbea942f6ba3a10b2fc074d0fb6c687cd04"},"schema_version":"1.0","source":{"id":"2404.11605","kind":"arxiv","version":1}},"canonical_sha256":"b2acbbe0600ac889dff6bfb5668217ee7002aaf416f4d8368c14a61825876f2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2acbbe0600ac889dff6bfb5668217ee7002aaf416f4d8368c14a61825876f2e","first_computed_at":"2026-07-05T08:09:10.758823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:10.758823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uD/RwEXGEW7OUDvUl1g/jPZJo3yzGtFUX686SW4IPSO6V7CoaHn5S1JNYuJciV82H/2O1jj1U/sCt442WiFlCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:10.759343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3784805d5fd0c8f7c17356245acec893f6995be330c6258457d346e4c6acd37","sha256:a3d8ea641b25cdb712ee6207f3554da1b8073398c6a3d77409bfcc536843ab25"],"state_sha256":"ded0bad70fb748a292f690760d4d0b01b4e92535a0291a6ecc9c57c163fddc7d"}