{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RIYUN5E7JWNTUF246GE4PHFM25","short_pith_number":"pith:RIYUN5E7","canonical_record":{"source":{"id":"2412.04383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:58:43Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"6809f3f9e7c34237aacff7f44aab6c29edcd4bd350634302b71af57cb2a07be8","abstract_canon_sha256":"6e80adee1cc49b71795bdcd82f93b4d2cedda2b280044017852a5cd4f482d969"},"schema_version":"1.0"},"canonical_sha256":"8a3146f49f4d9b3a175cf189c79cacd760a85358d22d83c51139e636a3124ed7","source":{"kind":"arxiv","id":"2412.04383","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04383","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04383v2","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04383","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"RIYUN5E7JWNT","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"RIYUN5E7JWNTUF24","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"RIYUN5E7","created_at":"2026-07-05T11:11:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RIYUN5E7JWNTUF246GE4PHFM25","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:58:43Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"6809f3f9e7c34237aacff7f44aab6c29edcd4bd350634302b71af57cb2a07be8","abstract_canon_sha256":"6e80adee1cc49b71795bdcd82f93b4d2cedda2b280044017852a5cd4f482d969"},"schema_version":"1.0"},"canonical_sha256":"8a3146f49f4d9b3a175cf189c79cacd760a85358d22d83c51139e636a3124ed7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:37.884668Z","signature_b64":"yz234lgQvtI7lA923PgS9KWn7mItXIQgNxLnazdBmcofhD4NIH5Nr8T0ZTF4TNAToHaiA4LhYBPUhbsvt1+kBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a3146f49f4d9b3a175cf189c79cacd760a85358d22d83c51139e636a3124ed7","last_reissued_at":"2026-07-05T11:11:37.884131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:37.884131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04383","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":"2026-07-05T11:11:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jxo8zb69frDyEjtgg3K+RfyJvGIEuY+Fa6uCW5egxwPgM0DMsAX0SbCxceeIkMqdoOa2NYVmbHKnJcJUHodjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:26:36.639156Z"},"content_sha256":"8266c4d30bcad9c27d1ce760607953fab31e92f17b5cba10a19a7f4a1009fbca","schema_version":"1.0","event_id":"sha256:8266c4d30bcad9c27d1ce760607953fab31e92f17b5cba10a19a7f4a1009fbca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RIYUN5E7JWNTUF246GE4PHFM25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","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":"2024-12-05T17:58:43Z","abstract_excerpt":"3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely on annotated 3D datasets and predefined object categories, limiting scalability and adaptability. To overcome these limitations, we introduce SeeGround, a zero-shot 3DVG framework leveraging 2D Vision-Language Models (VLMs) trained on large-scale 2D data. SeeGround represents 3D scenes as a hybrid of query-aligned rendered images and spatially enriched text descriptions, bridging the gap between 3D data an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04383","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/2412.04383/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":"2026-07-05T11:11:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E1q4rLNXXU5NfiqOhhIM/DWjgQkXcLv/BKF1YWE30FGyC7b3aXTILKyWvoFwF8BIx8SdIi+4/gfyTn9FjG2WDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:26:36.639679Z"},"content_sha256":"d9f0125970e9c8221709243ebe06e8c2122fd98101c9f5850c9f3aeefeb0998f","schema_version":"1.0","event_id":"sha256:d9f0125970e9c8221709243ebe06e8c2122fd98101c9f5850c9f3aeefeb0998f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RIYUN5E7JWNTUF246GE4PHFM25/bundle.json","state_url":"https://pith.science/pith/RIYUN5E7JWNTUF246GE4PHFM25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RIYUN5E7JWNTUF246GE4PHFM25/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":"2026-08-14T08:26:36Z","links":{"resolver":"https://pith.science/pith/RIYUN5E7JWNTUF246GE4PHFM25","bundle":"https://pith.science/pith/RIYUN5E7JWNTUF246GE4PHFM25/bundle.json","state":"https://pith.science/pith/RIYUN5E7JWNTUF246GE4PHFM25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RIYUN5E7JWNTUF246GE4PHFM25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RIYUN5E7JWNTUF246GE4PHFM25","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":"6e80adee1cc49b71795bdcd82f93b4d2cedda2b280044017852a5cd4f482d969","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:58:43Z","title_canon_sha256":"6809f3f9e7c34237aacff7f44aab6c29edcd4bd350634302b71af57cb2a07be8"},"schema_version":"1.0","source":{"id":"2412.04383","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04383","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04383v2","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04383","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"RIYUN5E7JWNT","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"RIYUN5E7JWNTUF24","created_at":"2026-07-05T11:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"RIYUN5E7","created_at":"2026-07-05T11:11:37Z"}],"graph_snapshots":[{"event_id":"sha256:d9f0125970e9c8221709243ebe06e8c2122fd98101c9f5850c9f3aeefeb0998f","target":"graph","created_at":"2026-07-05T11:11:37Z","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/2412.04383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely on annotated 3D datasets and predefined object categories, limiting scalability and adaptability. To overcome these limitations, we introduce SeeGround, a zero-shot 3DVG framework leveraging 2D Vision-Language Models (VLMs) trained on large-scale 2D data. SeeGround represents 3D scenes as a hybrid of query-aligned rendered images and spatially enriched text descriptions, bridging the gap between 3D data an","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":"2024-12-05T17:58:43Z","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04383","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":"sha256:8266c4d30bcad9c27d1ce760607953fab31e92f17b5cba10a19a7f4a1009fbca","target":"record","created_at":"2026-07-05T11:11:37Z","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":"6e80adee1cc49b71795bdcd82f93b4d2cedda2b280044017852a5cd4f482d969","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:58:43Z","title_canon_sha256":"6809f3f9e7c34237aacff7f44aab6c29edcd4bd350634302b71af57cb2a07be8"},"schema_version":"1.0","source":{"id":"2412.04383","kind":"arxiv","version":2}},"canonical_sha256":"8a3146f49f4d9b3a175cf189c79cacd760a85358d22d83c51139e636a3124ed7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a3146f49f4d9b3a175cf189c79cacd760a85358d22d83c51139e636a3124ed7","first_computed_at":"2026-07-05T11:11:37.884131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:37.884131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yz234lgQvtI7lA923PgS9KWn7mItXIQgNxLnazdBmcofhD4NIH5Nr8T0ZTF4TNAToHaiA4LhYBPUhbsvt1+kBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:37.884668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04383","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8266c4d30bcad9c27d1ce760607953fab31e92f17b5cba10a19a7f4a1009fbca","sha256:d9f0125970e9c8221709243ebe06e8c2122fd98101c9f5850c9f3aeefeb0998f"],"state_sha256":"f7104405f4b065a71d2b07fe3f112bfc640532e177e3b230713aa6bd67289de1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJ5LWSgu+Hgia5fZR/H6dUQ+xRHt+ihkuyBJl6FVWKGZy95tj9vOFDisN/F8NUwv9sHDPB7VT4uxBR1DrR4aDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:26:36.645293Z","bundle_sha256":"41f8d28c00f49ec017f3511dbcbcad25075963b2e3ae2536c60943f38bd777ff"}}