{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DNPLT7NJVG7KY5XXA2UEY2WWGX","short_pith_number":"pith:DNPLT7NJ","canonical_record":{"source":{"id":"2507.14904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T10:28:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"850198edca47d4625e8598c25ebc9b84a15680923e77633111033ec60ae319a5","abstract_canon_sha256":"606b0094e722aad191eb71edf6ebb29aebfb46b619594bcb6e0cf968e2bd13ad"},"schema_version":"1.0"},"canonical_sha256":"1b5eb9fda9a9beac76f706a84c6ad635e94a0001f5b81af44f03522c9a056d07","source":{"kind":"arxiv","id":"2507.14904","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14904","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14904v2","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14904","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"DNPLT7NJVG7K","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"DNPLT7NJVG7KY5XX","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"DNPLT7NJ","created_at":"2026-07-05T12:04:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DNPLT7NJVG7KY5XXA2UEY2WWGX","target":"record","payload":{"canonical_record":{"source":{"id":"2507.14904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T10:28:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"850198edca47d4625e8598c25ebc9b84a15680923e77633111033ec60ae319a5","abstract_canon_sha256":"606b0094e722aad191eb71edf6ebb29aebfb46b619594bcb6e0cf968e2bd13ad"},"schema_version":"1.0"},"canonical_sha256":"1b5eb9fda9a9beac76f706a84c6ad635e94a0001f5b81af44f03522c9a056d07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:38.660997Z","signature_b64":"LJ5H0gd82RvE6j9nltY+TTmnj2NM05EsIsLuzj/2RW8pcBQXcaMlv1toCKXNykrENBnuTE0CHydE03C2dxOwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b5eb9fda9a9beac76f706a84c6ad635e94a0001f5b81af44f03522c9a056d07","last_reissued_at":"2026-07-05T12:04:38.660332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:38.660332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.14904","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CWk6kLacwC9fFUspbOgLfwtFCZ6PUX49r47GZ7Ibq134oosZQZkLjt+0d1hJ8qFAu5esGOo7dr4hQENKuXQdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:17:43.829685Z"},"content_sha256":"ee8837350307fe9375b70646d3642793db96b43d0200031efe0c6e22d47d1327","schema_version":"1.0","event_id":"sha256:ee8837350307fe9375b70646d3642793db96b43d0200031efe0c6e22d47d1327"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DNPLT7NJVG7KY5XXA2UEY2WWGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fan Li, Guang Dai, Jingdong Wang, Mengmeng Wang, Zanyi Wang, Zeyi Huang","submitted_at":"2025-07-20T10:28:06Z","abstract_excerpt":"3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions, which is crucial for embodied intelligence. Existing 3D visual grounding methods typically rely on separate encoders for different modalities (e.g., RGB images, text, and 3D point clouds), resulting in large and complex models that are inefficient to train. While some approaches use pre-trained 2D multi-modal models like CLIP for 3D tasks, they still struggle with aligning point cloud data to 2D encoders. As a result, these methods continue to depend on 3D en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14904","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.14904/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jsj1/UkJyLoW05iA/xN5fZOvbsyBXTGcC+i9O6/Bv5/jAZ75fDDrPs4IhiAtmsAYI3QRZDbKXVnMfOGCaTFdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:17:43.830213Z"},"content_sha256":"f6459b0f21fa9136468efe1f3786e29092d1bad4bb512bed12fbbe488692f384","schema_version":"1.0","event_id":"sha256:f6459b0f21fa9136468efe1f3786e29092d1bad4bb512bed12fbbe488692f384"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DNPLT7NJVG7KY5XXA2UEY2WWGX/bundle.json","state_url":"https://pith.science/pith/DNPLT7NJVG7KY5XXA2UEY2WWGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DNPLT7NJVG7KY5XXA2UEY2WWGX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:17:43Z","links":{"resolver":"https://pith.science/pith/DNPLT7NJVG7KY5XXA2UEY2WWGX","bundle":"https://pith.science/pith/DNPLT7NJVG7KY5XXA2UEY2WWGX/bundle.json","state":"https://pith.science/pith/DNPLT7NJVG7KY5XXA2UEY2WWGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DNPLT7NJVG7KY5XXA2UEY2WWGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DNPLT7NJVG7KY5XXA2UEY2WWGX","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":"606b0094e722aad191eb71edf6ebb29aebfb46b619594bcb6e0cf968e2bd13ad","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T10:28:06Z","title_canon_sha256":"850198edca47d4625e8598c25ebc9b84a15680923e77633111033ec60ae319a5"},"schema_version":"1.0","source":{"id":"2507.14904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14904","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14904v2","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14904","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"DNPLT7NJVG7K","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"DNPLT7NJVG7KY5XX","created_at":"2026-07-05T12:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"DNPLT7NJ","created_at":"2026-07-05T12:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:f6459b0f21fa9136468efe1f3786e29092d1bad4bb512bed12fbbe488692f384","target":"graph","created_at":"2026-07-05T12:04:38Z","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/2507.14904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions, which is crucial for embodied intelligence. Existing 3D visual grounding methods typically rely on separate encoders for different modalities (e.g., RGB images, text, and 3D point clouds), resulting in large and complex models that are inefficient to train. While some approaches use pre-trained 2D multi-modal models like CLIP for 3D tasks, they still struggle with aligning point cloud data to 2D encoders. As a result, these methods continue to depend on 3D en","authors_text":"Fan Li, Guang Dai, Jingdong Wang, Mengmeng Wang, Zanyi Wang, Zeyi Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T10:28:06Z","title":"TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14904","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:ee8837350307fe9375b70646d3642793db96b43d0200031efe0c6e22d47d1327","target":"record","created_at":"2026-07-05T12:04:38Z","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":"606b0094e722aad191eb71edf6ebb29aebfb46b619594bcb6e0cf968e2bd13ad","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T10:28:06Z","title_canon_sha256":"850198edca47d4625e8598c25ebc9b84a15680923e77633111033ec60ae319a5"},"schema_version":"1.0","source":{"id":"2507.14904","kind":"arxiv","version":2}},"canonical_sha256":"1b5eb9fda9a9beac76f706a84c6ad635e94a0001f5b81af44f03522c9a056d07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b5eb9fda9a9beac76f706a84c6ad635e94a0001f5b81af44f03522c9a056d07","first_computed_at":"2026-07-05T12:04:38.660332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:38.660332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LJ5H0gd82RvE6j9nltY+TTmnj2NM05EsIsLuzj/2RW8pcBQXcaMlv1toCKXNykrENBnuTE0CHydE03C2dxOwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:38.660997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee8837350307fe9375b70646d3642793db96b43d0200031efe0c6e22d47d1327","sha256:f6459b0f21fa9136468efe1f3786e29092d1bad4bb512bed12fbbe488692f384"],"state_sha256":"c2e3831741f4ef91bd8b0c2a0213af44a8abd5378a72d36208e20265bb1b9d72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B/sKUCywv80H0SwVSRilLsJk86lZXA9iBG3/V9yCHM9qghbEY5esBArwW/r6gqvRWqH9tfUG+3qWmCD3+Yj+Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:17:43.836853Z","bundle_sha256":"53bcee2a97300616a22f22cf986118724038f1372aefbc5a08ae1230c818535e"}}