{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LBNX2EXJMZCWT75GM2BLFSE4KI","short_pith_number":"pith:LBNX2EXJ","canonical_record":{"source":{"id":"2506.21924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T05:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"53e749c68985fc4c5120c64b6e93da6e24ca615bacd9df7dff0a3fa20b968cbf","abstract_canon_sha256":"1d710b48ee4fed3d26cc2e2ec5c074bfe703c10700ddd12f398b83fa5bd9fa71"},"schema_version":"1.0"},"canonical_sha256":"585b7d12e9664569ffa66682b2c89c5212b70994444c2cc1806023b56610b4c9","source":{"kind":"arxiv","id":"2506.21924","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21924","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21924v1","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21924","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"pith_short_12","alias_value":"LBNX2EXJMZCW","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"pith_short_16","alias_value":"LBNX2EXJMZCWT75G","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"pith_short_8","alias_value":"LBNX2EXJ","created_at":"2026-07-05T11:28:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LBNX2EXJMZCWT75GM2BLFSE4KI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T05:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"53e749c68985fc4c5120c64b6e93da6e24ca615bacd9df7dff0a3fa20b968cbf","abstract_canon_sha256":"1d710b48ee4fed3d26cc2e2ec5c074bfe703c10700ddd12f398b83fa5bd9fa71"},"schema_version":"1.0"},"canonical_sha256":"585b7d12e9664569ffa66682b2c89c5212b70994444c2cc1806023b56610b4c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:18.496839Z","signature_b64":"vr3dsknw1tiTg3I53nkELhO9x/uTw0925mUVZY/JpN91sdJ+hCPtYA6nXrRKVG0ECQp+gVuaCVxky1Q7d0ZuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"585b7d12e9664569ffa66682b2c89c5212b70994444c2cc1806023b56610b4c9","last_reissued_at":"2026-07-05T11:28:18.496245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:18.496245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21924","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":"2026-07-05T11:28:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"djMtVcN4U85hzAFsPRZydoQZLHqLds7BYiriplesrkz6ZSorI1TQ1WCkWGsXJZh4PoDDbHHPkUC3MhbY2AE6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:42:33.229201Z"},"content_sha256":"b2891c40caa842c74469b1e731c0592c7681f896cd2825209ca7f84c7817858a","schema_version":"1.0","event_id":"sha256:b2891c40caa842c74469b1e731c0592c7681f896cd2825209ca7f84c7817858a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LBNX2EXJMZCWT75GM2BLFSE4KI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jingyi Liao, Rong-Cheng Tu, Shunyu Liu, Wenhao Sun, Xiao Luo, Zhao Jin","submitted_at":"2025-06-27T05:34:57Z","abstract_excerpt":"3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER - a VLM-driven agent that combines both modalities in a progressive reasoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21924","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/2506.21924/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":"2026-07-05T11:28:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k/6SGdRqweYVxBl5o42Msavz+B/quGODJME7yR9daD3nd+RfB5koXKNCIxwQogyFkJ3c7t8FXwMbIxN/271hCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:42:33.229599Z"},"content_sha256":"3e301b0672899b16b141737e79259ee0a7377c687bc05bb90f37ee1690721ba6","schema_version":"1.0","event_id":"sha256:3e301b0672899b16b141737e79259ee0a7377c687bc05bb90f37ee1690721ba6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/bundle.json","state_url":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/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":"2026-07-06T08:42:33Z","links":{"resolver":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI","bundle":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/bundle.json","state":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LBNX2EXJMZCWT75GM2BLFSE4KI","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":"1d710b48ee4fed3d26cc2e2ec5c074bfe703c10700ddd12f398b83fa5bd9fa71","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T05:34:57Z","title_canon_sha256":"53e749c68985fc4c5120c64b6e93da6e24ca615bacd9df7dff0a3fa20b968cbf"},"schema_version":"1.0","source":{"id":"2506.21924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21924","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21924v1","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21924","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"pith_short_12","alias_value":"LBNX2EXJMZCW","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"pith_short_16","alias_value":"LBNX2EXJMZCWT75G","created_at":"2026-07-05T11:28:18Z"},{"alias_kind":"pith_short_8","alias_value":"LBNX2EXJ","created_at":"2026-07-05T11:28:18Z"}],"graph_snapshots":[{"event_id":"sha256:3e301b0672899b16b141737e79259ee0a7377c687bc05bb90f37ee1690721ba6","target":"graph","created_at":"2026-07-05T11:28:18Z","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/2506.21924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER - a VLM-driven agent that combines both modalities in a progressive reasoning","authors_text":"Dacheng Tao, Jingyi Liao, Rong-Cheng Tu, Shunyu Liu, Wenhao Sun, Xiao Luo, Zhao Jin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T05:34:57Z","title":"SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21924","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:b2891c40caa842c74469b1e731c0592c7681f896cd2825209ca7f84c7817858a","target":"record","created_at":"2026-07-05T11:28:18Z","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":"1d710b48ee4fed3d26cc2e2ec5c074bfe703c10700ddd12f398b83fa5bd9fa71","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T05:34:57Z","title_canon_sha256":"53e749c68985fc4c5120c64b6e93da6e24ca615bacd9df7dff0a3fa20b968cbf"},"schema_version":"1.0","source":{"id":"2506.21924","kind":"arxiv","version":1}},"canonical_sha256":"585b7d12e9664569ffa66682b2c89c5212b70994444c2cc1806023b56610b4c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"585b7d12e9664569ffa66682b2c89c5212b70994444c2cc1806023b56610b4c9","first_computed_at":"2026-07-05T11:28:18.496245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:18.496245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vr3dsknw1tiTg3I53nkELhO9x/uTw0925mUVZY/JpN91sdJ+hCPtYA6nXrRKVG0ECQp+gVuaCVxky1Q7d0ZuAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:18.496839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2891c40caa842c74469b1e731c0592c7681f896cd2825209ca7f84c7817858a","sha256:3e301b0672899b16b141737e79259ee0a7377c687bc05bb90f37ee1690721ba6"],"state_sha256":"cf8f6046ec4cba503b45f60efc589b6e3e492361b9c4277079168866fc346985"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9cNsJLbNS93AVYb3tuLz33SjWo6kd0+NwSYo6sWxMw8sgi3TgGa4cnQoeRf0T72ZKJIUGrSn5KiQY3mhQwrrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:42:33.231650Z","bundle_sha256":"cc54b4a3dbdfe69afba92c0e9e03158af86f6036b1c45161980502ed8efdc93c"}}