{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YFPNZ7ES27DQY3T7RYZIXRRS5F","short_pith_number":"pith:YFPNZ7ES","canonical_record":{"source":{"id":"2506.14238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T06:53:15Z","cross_cats_sorted":[],"title_canon_sha256":"db14fcf3fa5ea0d990709f5d0f8c3314535e5ed56e31d6d9381d6ef7f65083ae","abstract_canon_sha256":"d9d523f6084da9bfd8d0b9323cef26bd3602bdcf337c53825017899f41171617"},"schema_version":"1.0"},"canonical_sha256":"c15edcfc92d7c70c6e7f8e328bc632e95f058ef94d34b935723d39f9f77e0917","source":{"kind":"arxiv","id":"2506.14238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14238","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14238v1","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14238","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"pith_short_12","alias_value":"YFPNZ7ES27DQ","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"pith_short_16","alias_value":"YFPNZ7ES27DQY3T7","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"pith_short_8","alias_value":"YFPNZ7ES","created_at":"2026-07-05T11:22:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YFPNZ7ES27DQY3T7RYZIXRRS5F","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T06:53:15Z","cross_cats_sorted":[],"title_canon_sha256":"db14fcf3fa5ea0d990709f5d0f8c3314535e5ed56e31d6d9381d6ef7f65083ae","abstract_canon_sha256":"d9d523f6084da9bfd8d0b9323cef26bd3602bdcf337c53825017899f41171617"},"schema_version":"1.0"},"canonical_sha256":"c15edcfc92d7c70c6e7f8e328bc632e95f058ef94d34b935723d39f9f77e0917","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:51.744960Z","signature_b64":"sejJUeOe3JfOnO395YYPcYw8sgd+aJmEqfAMBcm2sDZxBorzzb233i+iU62Hn8TLYvgtwRI6ia+uqzAIxtubDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c15edcfc92d7c70c6e7f8e328bc632e95f058ef94d34b935723d39f9f77e0917","last_reissued_at":"2026-07-05T11:22:51.744502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:51.744502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14238","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":"2026-07-05T11:22:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6pFS0Mmf3BPFNKbiBazTt04Jo3lW1mBOLGcs7kVAhLq1xMzcJ+s5rtCIiKZ/WIVzafLjBU9DITbDUeb8vh5YCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:17:21.723222Z"},"content_sha256":"f0d969876db084f71230ac601d8545d512b5d0cf449072743be2b27b2f987f36","schema_version":"1.0","event_id":"sha256:f0d969876db084f71230ac601d8545d512b5d0cf449072743be2b27b2f987f36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YFPNZ7ES27DQY3T7RYZIXRRS5F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Representation Space for 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honghua Chen, Liangliang Nan, Lipeng Gu, Mingqiang Wei, Yinuo Zheng","submitted_at":"2025-06-17T06:53:15Z","abstract_excerpt":"3D visual grounding (3DVG) is a critical task in scene understanding that aims to identify objects in 3D scenes based on text descriptions. However, existing methods rely on separately pre-trained vision and text encoders, resulting in a significant gap between the two modalities in terms of spatial geometry and semantic categories. This discrepancy often causes errors in object positioning and classification. The paper proposes UniSpace-3D, which innovatively introduces a unified representation space for 3DVG, effectively bridging the gap between visual and textual features. Specifically, Uni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14238","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/2506.14238/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":"2026-07-05T11:22:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zoxE0+aXtMUOGRdNGlY0LDmVsvtMLxCqbQQXqteiEre8XAbFiZoaQHrs/aV2Dtd60hPtcION1JyPEtEYgTU0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:17:21.723882Z"},"content_sha256":"2b182ce4be612c44cbe820929996006b1a484300cf4cee76a83bf76428dde7ef","schema_version":"1.0","event_id":"sha256:2b182ce4be612c44cbe820929996006b1a484300cf4cee76a83bf76428dde7ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFPNZ7ES27DQY3T7RYZIXRRS5F/bundle.json","state_url":"https://pith.science/pith/YFPNZ7ES27DQY3T7RYZIXRRS5F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFPNZ7ES27DQY3T7RYZIXRRS5F/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":"2026-08-06T18:17:21Z","links":{"resolver":"https://pith.science/pith/YFPNZ7ES27DQY3T7RYZIXRRS5F","bundle":"https://pith.science/pith/YFPNZ7ES27DQY3T7RYZIXRRS5F/bundle.json","state":"https://pith.science/pith/YFPNZ7ES27DQY3T7RYZIXRRS5F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFPNZ7ES27DQY3T7RYZIXRRS5F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YFPNZ7ES27DQY3T7RYZIXRRS5F","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":"d9d523f6084da9bfd8d0b9323cef26bd3602bdcf337c53825017899f41171617","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T06:53:15Z","title_canon_sha256":"db14fcf3fa5ea0d990709f5d0f8c3314535e5ed56e31d6d9381d6ef7f65083ae"},"schema_version":"1.0","source":{"id":"2506.14238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14238","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14238v1","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14238","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"pith_short_12","alias_value":"YFPNZ7ES27DQ","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"pith_short_16","alias_value":"YFPNZ7ES27DQY3T7","created_at":"2026-07-05T11:22:51Z"},{"alias_kind":"pith_short_8","alias_value":"YFPNZ7ES","created_at":"2026-07-05T11:22:51Z"}],"graph_snapshots":[{"event_id":"sha256:2b182ce4be612c44cbe820929996006b1a484300cf4cee76a83bf76428dde7ef","target":"graph","created_at":"2026-07-05T11:22:51Z","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/2506.14238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D visual grounding (3DVG) is a critical task in scene understanding that aims to identify objects in 3D scenes based on text descriptions. However, existing methods rely on separately pre-trained vision and text encoders, resulting in a significant gap between the two modalities in terms of spatial geometry and semantic categories. This discrepancy often causes errors in object positioning and classification. The paper proposes UniSpace-3D, which innovatively introduces a unified representation space for 3DVG, effectively bridging the gap between visual and textual features. Specifically, Uni","authors_text":"Honghua Chen, Liangliang Nan, Lipeng Gu, Mingqiang Wei, Yinuo Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T06:53:15Z","title":"Unified Representation Space for 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14238","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:f0d969876db084f71230ac601d8545d512b5d0cf449072743be2b27b2f987f36","target":"record","created_at":"2026-07-05T11:22:51Z","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":"d9d523f6084da9bfd8d0b9323cef26bd3602bdcf337c53825017899f41171617","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T06:53:15Z","title_canon_sha256":"db14fcf3fa5ea0d990709f5d0f8c3314535e5ed56e31d6d9381d6ef7f65083ae"},"schema_version":"1.0","source":{"id":"2506.14238","kind":"arxiv","version":1}},"canonical_sha256":"c15edcfc92d7c70c6e7f8e328bc632e95f058ef94d34b935723d39f9f77e0917","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c15edcfc92d7c70c6e7f8e328bc632e95f058ef94d34b935723d39f9f77e0917","first_computed_at":"2026-07-05T11:22:51.744502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:51.744502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sejJUeOe3JfOnO395YYPcYw8sgd+aJmEqfAMBcm2sDZxBorzzb233i+iU62Hn8TLYvgtwRI6ia+uqzAIxtubDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:51.744960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0d969876db084f71230ac601d8545d512b5d0cf449072743be2b27b2f987f36","sha256:2b182ce4be612c44cbe820929996006b1a484300cf4cee76a83bf76428dde7ef"],"state_sha256":"1699a0eb027d50b3cb2297d29c263971e54e71c7db569a1ce8d441951a76a1f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GTqGVK94tJPTfD1/Yuclwdk2n8QHR0J8XDoioN8SFdv0IU/2qBu2jT80h1ZFZrB2RmFwewqR08glUN0VqOY9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:17:21.727560Z","bundle_sha256":"f96b0f64bf334c5c3cdf353038156ca8967410c9380ebf0b1750afa49fef3c09"}}