{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AIVOO2YG27KXAE5UIFM7YEVBN4","short_pith_number":"pith:AIVOO2YG","canonical_record":{"source":{"id":"2505.04058","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T02:02:15Z","cross_cats_sorted":[],"title_canon_sha256":"a8cabd0bcb7c5505f1adbb9cb2af4008bc34ca23f5f54ec28c0779253426fe0b","abstract_canon_sha256":"15fe4b82d54bcd7ecb3a4d6c9af2a19c87f8a83bd82e70e43b43b37503a4d6ee"},"schema_version":"1.0"},"canonical_sha256":"022ae76b06d7d57013b44159fc12a16f2c48c7112ef31d442da93ddaee2900d4","source":{"kind":"arxiv","id":"2505.04058","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04058","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04058v3","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04058","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_12","alias_value":"AIVOO2YG27KX","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_16","alias_value":"AIVOO2YG27KXAE5U","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_8","alias_value":"AIVOO2YG","created_at":"2026-07-05T11:54:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AIVOO2YG27KXAE5UIFM7YEVBN4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.04058","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T02:02:15Z","cross_cats_sorted":[],"title_canon_sha256":"a8cabd0bcb7c5505f1adbb9cb2af4008bc34ca23f5f54ec28c0779253426fe0b","abstract_canon_sha256":"15fe4b82d54bcd7ecb3a4d6c9af2a19c87f8a83bd82e70e43b43b37503a4d6ee"},"schema_version":"1.0"},"canonical_sha256":"022ae76b06d7d57013b44159fc12a16f2c48c7112ef31d442da93ddaee2900d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:11.883365Z","signature_b64":"+dt+Xpa/5kFFDD4mMoNNjLs6yFqOfXSgR0g+PyxrxJ93ynlDXRMgnL0gZaauXiv1Lk8vByoAk6NWlL70e4HUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"022ae76b06d7d57013b44159fc12a16f2c48c7112ef31d442da93ddaee2900d4","last_reissued_at":"2026-07-05T11:54:11.882938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:11.882938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.04058","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:54:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jjqqvJx+aSiymwTeo4vWGFmdLAW0HLsD+aq1EwoslRGFtLSO5Ap4fc97mVE+6BjB3XR8yXZA300WxXG67omuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:48:21.787761Z"},"content_sha256":"83873999ddf361140ff88c9d327ab90c076fe981a498f058349fbee886d64470","schema_version":"1.0","event_id":"sha256:83873999ddf361140ff88c9d327ab90c076fe981a498f058349fbee886d64470"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AIVOO2YG27KXAE5UIFM7YEVBN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Xiao, Guocan Zhao, Hongbin Xu, Wenxiong Kang","submitted_at":"2025-05-07T02:02:15Z","abstract_excerpt":"3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the described spatial relationships. Current methods attempt to achieve cross-modal understanding in complex scenes via a target-centered learning mechanism, ignoring the modeling of referred objects. We propose a novel 3D visual grounding framework that constructs language-guided scene graphs with referred object discrimination to improve relational perception. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04058","kind":"arxiv","version":3},"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/2505.04058/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":"2026-07-05T11:54:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6mUYOCmiSEkswrCEkAQLcIczdEJo6Yg2x4JTt/6OZqP/7Lq3G3LNrgbF2ztFj8piH6nH7Krqhemrby+w36nvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:48:21.788347Z"},"content_sha256":"038cb5aab217119f6f7b213fdfad32a53a3726ffd8aca749b3e311002ced6ac5","schema_version":"1.0","event_id":"sha256:038cb5aab217119f6f7b213fdfad32a53a3726ffd8aca749b3e311002ced6ac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/bundle.json","state_url":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/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":"2026-08-21T13:48:21Z","links":{"resolver":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4","bundle":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/bundle.json","state":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AIVOO2YG27KXAE5UIFM7YEVBN4","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":"15fe4b82d54bcd7ecb3a4d6c9af2a19c87f8a83bd82e70e43b43b37503a4d6ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T02:02:15Z","title_canon_sha256":"a8cabd0bcb7c5505f1adbb9cb2af4008bc34ca23f5f54ec28c0779253426fe0b"},"schema_version":"1.0","source":{"id":"2505.04058","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04058","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04058v3","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04058","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_12","alias_value":"AIVOO2YG27KX","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_16","alias_value":"AIVOO2YG27KXAE5U","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_8","alias_value":"AIVOO2YG","created_at":"2026-07-05T11:54:11Z"}],"graph_snapshots":[{"event_id":"sha256:038cb5aab217119f6f7b213fdfad32a53a3726ffd8aca749b3e311002ced6ac5","target":"graph","created_at":"2026-07-05T11:54:11Z","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/2505.04058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the described spatial relationships. Current methods attempt to achieve cross-modal understanding in complex scenes via a target-centered learning mechanism, ignoring the modeling of referred objects. We propose a novel 3D visual grounding framework that constructs language-guided scene graphs with referred object discrimination to improve relational perception. The","authors_text":"Feng Xiao, Guocan Zhao, Hongbin Xu, Wenxiong Kang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T02:02:15Z","title":"LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04058","kind":"arxiv","version":3},"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":"sha256:83873999ddf361140ff88c9d327ab90c076fe981a498f058349fbee886d64470","target":"record","created_at":"2026-07-05T11:54:11Z","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":"15fe4b82d54bcd7ecb3a4d6c9af2a19c87f8a83bd82e70e43b43b37503a4d6ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T02:02:15Z","title_canon_sha256":"a8cabd0bcb7c5505f1adbb9cb2af4008bc34ca23f5f54ec28c0779253426fe0b"},"schema_version":"1.0","source":{"id":"2505.04058","kind":"arxiv","version":3}},"canonical_sha256":"022ae76b06d7d57013b44159fc12a16f2c48c7112ef31d442da93ddaee2900d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"022ae76b06d7d57013b44159fc12a16f2c48c7112ef31d442da93ddaee2900d4","first_computed_at":"2026-07-05T11:54:11.882938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:11.882938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+dt+Xpa/5kFFDD4mMoNNjLs6yFqOfXSgR0g+PyxrxJ93ynlDXRMgnL0gZaauXiv1Lk8vByoAk6NWlL70e4HUBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:11.883365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04058","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83873999ddf361140ff88c9d327ab90c076fe981a498f058349fbee886d64470","sha256:038cb5aab217119f6f7b213fdfad32a53a3726ffd8aca749b3e311002ced6ac5"],"state_sha256":"0bcb21a4bc4ff5222d0a5ee318b2ea130cbc0d0393607a931bc3b6e255db3014"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bKeYwRflG0FrZSz1CCV7VKE4aAFMseICcinJZaQt43+btowJm3COV7OE+i0Y1q4u99qYd9p+dSyqNAIyQjKRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T13:48:21.794182Z","bundle_sha256":"f943889a5841503fb7a2b5f19752f1830b08adc8b5ea0714bb5756d4281d2829"}}