{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Z7XHHHNSSSQPU45DOVVEGNEMUU","short_pith_number":"pith:Z7XHHHNS","canonical_record":{"source":{"id":"2608.03763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T14:51:15Z","cross_cats_sorted":[],"title_canon_sha256":"fa1cf8e74fe9239c4c706c8a35a62fc211e15abb132f3a6a683d57de49d40477","abstract_canon_sha256":"e32409c6d832b70dd26aa9837c8117a95cd579ace3a6c45754fe67333d790457"},"schema_version":"1.0"},"canonical_sha256":"cfee739db294a0fa73a3756a43348ca5223cd512643a401726479702f9f7d4a7","source":{"kind":"arxiv","id":"2608.03763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03763","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03763v1","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03763","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z7XHHHNSSSQP","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z7XHHHNSSSQPU45D","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z7XHHHNS","created_at":"2026-08-05T01:37:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Z7XHHHNSSSQPU45DOVVEGNEMUU","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T14:51:15Z","cross_cats_sorted":[],"title_canon_sha256":"fa1cf8e74fe9239c4c706c8a35a62fc211e15abb132f3a6a683d57de49d40477","abstract_canon_sha256":"e32409c6d832b70dd26aa9837c8117a95cd579ace3a6c45754fe67333d790457"},"schema_version":"1.0"},"canonical_sha256":"cfee739db294a0fa73a3756a43348ca5223cd512643a401726479702f9f7d4a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:02.849885Z","signature_b64":"k8cB785bAIJ6kcdQHLhV8j0+yNJsVEjF3CgL7dM4mvnuaN0XAog5o+/sOf/LB2PcHdCuzaUeVI4lV4J12ttUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfee739db294a0fa73a3756a43348ca5223cd512643a401726479702f9f7d4a7","last_reissued_at":"2026-08-05T01:37:02.848517Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:02.848517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03763","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T01:37:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8FsBEbSZ9Ajgbra59Hnwntr9wBWjgsfjadhd8oUPMLRUv9iR2m7uRXyVY8yt7ziJj978rTlGXm8dAxPHMCAADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:16:32.881163Z"},"content_sha256":"ea3fa18c7d781bff2423fc7982fee2231791bd3cac4e292fc6271bcfad666c14","schema_version":"1.0","event_id":"sha256:ea3fa18c7d781bff2423fc7982fee2231791bd3cac4e292fc6271bcfad666c14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Z7XHHHNSSSQPU45DOVVEGNEMUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TDVR: Joint Text Disambiguation and Viewpoint Reasoning for Zero-Shot 3D Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junbo Wang, Qingxi Du, Yining Zhu, Yuke Li","submitted_at":"2026-08-04T14:51:15Z","abstract_excerpt":"Zero-shot 3D visual grounding aims to localize specific objects based on textual descriptions and 3D visual input. However, the effectiveness of existing methods is significantly hindered by the ambiguous query text and deficient viewpoints. To address these issues, we propose TDVR, a training-free reasoning framework that disambiguates the input text and infers accurate viewpoints for zero-shot 3D visual grounding. First, we construct semantic 3D scene graph from the detected instances in the 3D point cloud. Subsequently, we put the original query, appearance and spatial relationship descript"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03763","kind":"arxiv","version":1},"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/2608.03763/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":"2026-08-05T01:37:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BJt0lSxsNVZEpVcG5xsR7uJLG+w2RRafjf0dzIu4fJqsgh83WqgLVlCfk15Rw6eOqj1arid0K11qRrqb3gTbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:16:32.881818Z"},"content_sha256":"9be1757317c7a4f9719a4afbe1acd22b5d47ec24cafac8508449d3f14bb3602d","schema_version":"1.0","event_id":"sha256:9be1757317c7a4f9719a4afbe1acd22b5d47ec24cafac8508449d3f14bb3602d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z7XHHHNSSSQPU45DOVVEGNEMUU/bundle.json","state_url":"https://pith.science/pith/Z7XHHHNSSSQPU45DOVVEGNEMUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z7XHHHNSSSQPU45DOVVEGNEMUU/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":"2026-08-09T04:16:32Z","links":{"resolver":"https://pith.science/pith/Z7XHHHNSSSQPU45DOVVEGNEMUU","bundle":"https://pith.science/pith/Z7XHHHNSSSQPU45DOVVEGNEMUU/bundle.json","state":"https://pith.science/pith/Z7XHHHNSSSQPU45DOVVEGNEMUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z7XHHHNSSSQPU45DOVVEGNEMUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z7XHHHNSSSQPU45DOVVEGNEMUU","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":"e32409c6d832b70dd26aa9837c8117a95cd579ace3a6c45754fe67333d790457","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T14:51:15Z","title_canon_sha256":"fa1cf8e74fe9239c4c706c8a35a62fc211e15abb132f3a6a683d57de49d40477"},"schema_version":"1.0","source":{"id":"2608.03763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03763","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03763v1","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03763","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z7XHHHNSSSQP","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z7XHHHNSSSQPU45D","created_at":"2026-08-05T01:37:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z7XHHHNS","created_at":"2026-08-05T01:37:02Z"}],"graph_snapshots":[{"event_id":"sha256:9be1757317c7a4f9719a4afbe1acd22b5d47ec24cafac8508449d3f14bb3602d","target":"graph","created_at":"2026-08-05T01:37:02Z","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/2608.03763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot 3D visual grounding aims to localize specific objects based on textual descriptions and 3D visual input. However, the effectiveness of existing methods is significantly hindered by the ambiguous query text and deficient viewpoints. To address these issues, we propose TDVR, a training-free reasoning framework that disambiguates the input text and infers accurate viewpoints for zero-shot 3D visual grounding. First, we construct semantic 3D scene graph from the detected instances in the 3D point cloud. Subsequently, we put the original query, appearance and spatial relationship descript","authors_text":"Junbo Wang, Qingxi Du, Yining Zhu, Yuke Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T14:51:15Z","title":"TDVR: Joint Text Disambiguation and Viewpoint Reasoning for Zero-Shot 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03763","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:ea3fa18c7d781bff2423fc7982fee2231791bd3cac4e292fc6271bcfad666c14","target":"record","created_at":"2026-08-05T01:37:02Z","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":"e32409c6d832b70dd26aa9837c8117a95cd579ace3a6c45754fe67333d790457","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T14:51:15Z","title_canon_sha256":"fa1cf8e74fe9239c4c706c8a35a62fc211e15abb132f3a6a683d57de49d40477"},"schema_version":"1.0","source":{"id":"2608.03763","kind":"arxiv","version":1}},"canonical_sha256":"cfee739db294a0fa73a3756a43348ca5223cd512643a401726479702f9f7d4a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfee739db294a0fa73a3756a43348ca5223cd512643a401726479702f9f7d4a7","first_computed_at":"2026-08-05T01:37:02.848517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:37:02.848517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k8cB785bAIJ6kcdQHLhV8j0+yNJsVEjF3CgL7dM4mvnuaN0XAog5o+/sOf/LB2PcHdCuzaUeVI4lV4J12ttUCg==","signature_status":"signed_v1","signed_at":"2026-08-05T01:37:02.849885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea3fa18c7d781bff2423fc7982fee2231791bd3cac4e292fc6271bcfad666c14","sha256:9be1757317c7a4f9719a4afbe1acd22b5d47ec24cafac8508449d3f14bb3602d"],"state_sha256":"7bf9b8ed45e6cdbe5b1fc243339c9646afcadfc1aed48d6b49c002d68b29ceb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FBVidEdJcCqxgAV4+YFTxksfpfnNjH18ClkEA5wwsgQJvG5LXhjLB/pz8S2XLHt/X5YmVJKMuyKnGz9qbQMNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:16:32.888555Z","bundle_sha256":"781f2bcfa8b4f8aa4737e947b2282b6bdd39febeef7fd424dda05b0b660a6003"}}