{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7KMO7XYD4464GGI25ATUKCDZT2","short_pith_number":"pith:7KMO7XYD","canonical_record":{"source":{"id":"2505.22429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T14:53:53Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"71b8a03e81630a62764b1a7cb7cdd32b8e96213dd3afd7dd3d2186b4e6a87ef7","abstract_canon_sha256":"9949a66e012c3edb440bbec59d16cf6b288aef13e6d2846f5384abac8767afd0"},"schema_version":"1.0"},"canonical_sha256":"fa98efdf03e73dc3191ae8274508799e928a0cd3410f26ecf30f6bf28278f444","source":{"kind":"arxiv","id":"2505.22429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22429","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22429v1","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22429","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"7KMO7XYD4464","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"7KMO7XYD4464GGI2","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"7KMO7XYD","created_at":"2026-07-05T11:11:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7KMO7XYD4464GGI25ATUKCDZT2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T14:53:53Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"71b8a03e81630a62764b1a7cb7cdd32b8e96213dd3afd7dd3d2186b4e6a87ef7","abstract_canon_sha256":"9949a66e012c3edb440bbec59d16cf6b288aef13e6d2846f5384abac8767afd0"},"schema_version":"1.0"},"canonical_sha256":"fa98efdf03e73dc3191ae8274508799e928a0cd3410f26ecf30f6bf28278f444","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:23.887050Z","signature_b64":"/O4ddjmmt6OtJFQ7XRW6OFW0kmbqIZaKNUYNIHszTFmFp0pdLqd3HTfoOY69aVy3hrvkmJfN3B+ARwFUfzQsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa98efdf03e73dc3191ae8274508799e928a0cd3410f26ecf30f6bf28278f444","last_reissued_at":"2026-07-05T11:11:23.886542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:23.886542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22429","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":"2026-07-05T11:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wn3G0T0H5apsNHVaREVOz326mXL7MTpcj9EN5ND+7peCeo1n9KJZCBJdG208e+posHkhcddLvF+5A8Cu38+qCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:58:10.499566Z"},"content_sha256":"7d6127f558d3d42ab1a5e1f418437811be7a1a1cec5b9d657629a19a4de4ac96","schema_version":"1.0","event_id":"sha256:7d6127f558d3d42ab1a5e1f418437811be7a1a1cec5b9d657629a19a4de4ac96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7KMO7XYD4464GGI25ATUKCDZT2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot 3D Visual Grounding from Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Junwei Liang, Lingdong Kong, Rong Li, Shijie Li, Xulei Yang","submitted_at":"2025-05-28T14:53:53Z","abstract_excerpt":"3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions, enabling downstream applications such as augmented reality and robotics. Existing approaches typically rely on labeled 3D data and predefined categories, limiting scalability to open-world settings. We present SeeGround, a zero-shot 3DVG framework that leverages 2D Vision-Language Models (VLMs) to bypass the need for 3D-specific training. To bridge the modality gap, we introduce a hybrid input format that pairs query-aligned rendered views with spatially enriched textual descriptions. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22429","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/2505.22429/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":"2026-07-05T11:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVLmOjw2dRi3/kxSSvLeBUjU/RLK1INhxYqgyypHic/yGoo4DzgvKfEn6z5IVCbcdBkle08oUghyXS4FK5LCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:58:10.500062Z"},"content_sha256":"350d4825445937a03edff9c7ac59da23c8257fdeb044122ddc0090b0ff0b2c93","schema_version":"1.0","event_id":"sha256:350d4825445937a03edff9c7ac59da23c8257fdeb044122ddc0090b0ff0b2c93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7KMO7XYD4464GGI25ATUKCDZT2/bundle.json","state_url":"https://pith.science/pith/7KMO7XYD4464GGI25ATUKCDZT2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7KMO7XYD4464GGI25ATUKCDZT2/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":"2026-08-08T13:58:10Z","links":{"resolver":"https://pith.science/pith/7KMO7XYD4464GGI25ATUKCDZT2","bundle":"https://pith.science/pith/7KMO7XYD4464GGI25ATUKCDZT2/bundle.json","state":"https://pith.science/pith/7KMO7XYD4464GGI25ATUKCDZT2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7KMO7XYD4464GGI25ATUKCDZT2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7KMO7XYD4464GGI25ATUKCDZT2","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":"9949a66e012c3edb440bbec59d16cf6b288aef13e6d2846f5384abac8767afd0","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T14:53:53Z","title_canon_sha256":"71b8a03e81630a62764b1a7cb7cdd32b8e96213dd3afd7dd3d2186b4e6a87ef7"},"schema_version":"1.0","source":{"id":"2505.22429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22429","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22429v1","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22429","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"7KMO7XYD4464","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"7KMO7XYD4464GGI2","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"7KMO7XYD","created_at":"2026-07-05T11:11:23Z"}],"graph_snapshots":[{"event_id":"sha256:350d4825445937a03edff9c7ac59da23c8257fdeb044122ddc0090b0ff0b2c93","target":"graph","created_at":"2026-07-05T11:11:23Z","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/2505.22429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions, enabling downstream applications such as augmented reality and robotics. Existing approaches typically rely on labeled 3D data and predefined categories, limiting scalability to open-world settings. We present SeeGround, a zero-shot 3DVG framework that leverages 2D Vision-Language Models (VLMs) to bypass the need for 3D-specific training. To bridge the modality gap, we introduce a hybrid input format that pairs query-aligned rendered views with spatially enriched textual descriptions. Ou","authors_text":"Junwei Liang, Lingdong Kong, Rong Li, Shijie Li, Xulei Yang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T14:53:53Z","title":"Zero-Shot 3D Visual Grounding from Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22429","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":"sha256:7d6127f558d3d42ab1a5e1f418437811be7a1a1cec5b9d657629a19a4de4ac96","target":"record","created_at":"2026-07-05T11:11:23Z","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":"9949a66e012c3edb440bbec59d16cf6b288aef13e6d2846f5384abac8767afd0","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T14:53:53Z","title_canon_sha256":"71b8a03e81630a62764b1a7cb7cdd32b8e96213dd3afd7dd3d2186b4e6a87ef7"},"schema_version":"1.0","source":{"id":"2505.22429","kind":"arxiv","version":1}},"canonical_sha256":"fa98efdf03e73dc3191ae8274508799e928a0cd3410f26ecf30f6bf28278f444","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa98efdf03e73dc3191ae8274508799e928a0cd3410f26ecf30f6bf28278f444","first_computed_at":"2026-07-05T11:11:23.886542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:23.886542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/O4ddjmmt6OtJFQ7XRW6OFW0kmbqIZaKNUYNIHszTFmFp0pdLqd3HTfoOY69aVy3hrvkmJfN3B+ARwFUfzQsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:23.887050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d6127f558d3d42ab1a5e1f418437811be7a1a1cec5b9d657629a19a4de4ac96","sha256:350d4825445937a03edff9c7ac59da23c8257fdeb044122ddc0090b0ff0b2c93"],"state_sha256":"126094cb5c86ded38122535075beaabd89b4aa0b5057738992792fef22377fac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d3KNWNRciKCiPsvbDjv8gcXcJaRbgG5xkFN3Gx/HKeHL9KZPXFDzriDg4JTSkIRzJhplzavBE6YdBRRBddH5Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:58:10.503712Z","bundle_sha256":"556fe92d065dee63e116a8e7b6126298581e47e200c4e3332e0cd66697d09239"}}