{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QGSAS7CCDK5J2XP6HTWX5QJQPZ","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":"8d2762e6a67af18156bea46601740849224a0cd6b6a60e26244b68440f851061","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T07:26:51Z","title_canon_sha256":"58c7e0fdd3d0a7e9e33510070b9b1ace95fc89acbb66eea5be2078ceaffa4887"},"schema_version":"1.0","source":{"id":"2308.10185","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10185","created_at":"2026-07-05T08:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10185v2","created_at":"2026-07-05T08:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10185","created_at":"2026-07-05T08:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"QGSAS7CCDK5J","created_at":"2026-07-05T08:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"QGSAS7CCDK5J2XP6","created_at":"2026-07-05T08:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"QGSAS7CC","created_at":"2026-07-05T08:00:35Z"}],"graph_snapshots":[{"event_id":"sha256:2b72e1edc15088367cfdb9c3890b916385f972942cdc1c147e755f1fd67a39bd","target":"graph","created_at":"2026-07-05T08:00:35Z","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/2308.10185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Though the success of CLIP-based training recipes in vision-language models, their scalability to more modalities (e.g., 3D, audio, etc.) is limited to large-scale data, which is expensive or even inapplicable for rare modalities. In this paper, we present ViT-Lens that facilitates efficient omni-modal representation learning by perceiving novel modalities with a pretrained ViT and aligning to a pre-defined space. Specifically, the modality-specific lens is tuned to project multimodal signals to the shared embedding space, which are then processed by a strong ViT that carries pre-trained image","authors_text":"Dylan Sun, Jianfeng Zhang, Kun Yi, Mike Zheng Shou, Weixian Lei, Ying Shan, Yixiao Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T07:26:51Z","title":"ViT-Lens: Initiating Omni-Modal Exploration through 3D Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10185","kind":"arxiv","version":2},"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:e39af35ee742c08a945ea9cc92a134a414417a15ec0814fac2bdd0eb9663408d","target":"record","created_at":"2026-07-05T08:00:35Z","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":"8d2762e6a67af18156bea46601740849224a0cd6b6a60e26244b68440f851061","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T07:26:51Z","title_canon_sha256":"58c7e0fdd3d0a7e9e33510070b9b1ace95fc89acbb66eea5be2078ceaffa4887"},"schema_version":"1.0","source":{"id":"2308.10185","kind":"arxiv","version":2}},"canonical_sha256":"81a4097c421aba9d5dfe3ced7ec1307e4d5a4c9bb8a0bce39dae768561b0959a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81a4097c421aba9d5dfe3ced7ec1307e4d5a4c9bb8a0bce39dae768561b0959a","first_computed_at":"2026-07-05T08:00:35.186300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:35.186300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NX4wUcNIJklN17ZnlC8hOyIl82dm1HQsenu3U1MQ6RteEDf5QZhdwvaCM2NgR8h4QxGjC7uzQWXmmitx2uJIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:35.186802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10185","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e39af35ee742c08a945ea9cc92a134a414417a15ec0814fac2bdd0eb9663408d","sha256:2b72e1edc15088367cfdb9c3890b916385f972942cdc1c147e755f1fd67a39bd"],"state_sha256":"bc2a4f830a7da4bec7c94f20beecf180584ad1a5584c3d9c3d3f27bc988a158c"}