{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EI4WX4QYA4XVAHU7ORKD4NYZOF","short_pith_number":"pith:EI4WX4QY","canonical_record":{"source":{"id":"2605.21788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:30:51Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"29e5f99aa779767fc76481df8a112687199659d4a425010f26053ef62f12c660","abstract_canon_sha256":"3679eb95284592a7e57530aa095be18d104340d2541501aa2549e72c22cc9cc1"},"schema_version":"1.0"},"canonical_sha256":"22396bf218072f501e9f74543e3719715f09f4ca76993c1cfbb619a3dfcfd03e","source":{"kind":"arxiv","id":"2605.21788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21788","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21788v1","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21788","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"EI4WX4QYA4XV","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"EI4WX4QYA4XVAHU7","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"EI4WX4QY","created_at":"2026-05-22T01:03:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EI4WX4QYA4XVAHU7ORKD4NYZOF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:30:51Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"29e5f99aa779767fc76481df8a112687199659d4a425010f26053ef62f12c660","abstract_canon_sha256":"3679eb95284592a7e57530aa095be18d104340d2541501aa2549e72c22cc9cc1"},"schema_version":"1.0"},"canonical_sha256":"22396bf218072f501e9f74543e3719715f09f4ca76993c1cfbb619a3dfcfd03e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:32.470826Z","signature_b64":"deiZA7MzSDX9cDVCWeLNjUQoW/BQaD7p/72b7HKHis+vDZvaKD6llXpk53nKnMzsox052yoJQLM6S6BquaekAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22396bf218072f501e9f74543e3719715f09f4ca76993c1cfbb619a3dfcfd03e","last_reissued_at":"2026-05-22T01:03:32.470159Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:32.470159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21788","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":"2026-05-22T01:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ygSh+1METxaJR0JEq7Y2ZioGTfGh543KxDAuKofh30ZmwKW4820NYlPNNMpJl/g25I3+sEGc0+70j32jborjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T04:53:10.480623Z"},"content_sha256":"68f4edfacc43f935ca695c44fa37472fa091964f547da66691641fb89a2243db","schema_version":"1.0","event_id":"sha256:68f4edfacc43f935ca695c44fa37472fa091964f547da66691641fb89a2243db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EI4WX4QYA4XVAHU7ORKD4NYZOF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Brendan Crowe, Christoffer Heckman, Doncey Albin, Xuefei Sun, Xujia Zhang","submitted_at":"2026-05-20T22:30:51Z","abstract_excerpt":"Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VLM) approaches achieve promising results but rely on view-dependent reasoning or implicit representations, limiting spatial consistency and interpretability for compositional queries. We propose SceneGraphGrounder, a framework that reformulates 3D grounding as structured graph matching over a reconstructed 3D scene graph. To enable this formulation, we introduce a visual marker prompting strategy that enables a VLM to infer object-object relatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21788","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/2605.21788/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":"2026-05-22T01:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vMTkF1/xtdlmi9NsXfANGft1VPQjxeaDpkbm99/rGwa3w7RIo+JE0xCVKFcnkWpo0XTojkt84NnbBMrUvQTCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T04:53:10.481537Z"},"content_sha256":"be9f999dd32656d4a4b60bc87a47c0dda6c1d38200e36d0444eebe583b3e60fb","schema_version":"1.0","event_id":"sha256:be9f999dd32656d4a4b60bc87a47c0dda6c1d38200e36d0444eebe583b3e60fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/bundle.json","state_url":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/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":"2026-05-24T04:53:10Z","links":{"resolver":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF","bundle":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/bundle.json","state":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EI4WX4QYA4XVAHU7ORKD4NYZOF","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":"3679eb95284592a7e57530aa095be18d104340d2541501aa2549e72c22cc9cc1","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:30:51Z","title_canon_sha256":"29e5f99aa779767fc76481df8a112687199659d4a425010f26053ef62f12c660"},"schema_version":"1.0","source":{"id":"2605.21788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21788","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21788v1","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21788","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"EI4WX4QYA4XV","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"EI4WX4QYA4XVAHU7","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"EI4WX4QY","created_at":"2026-05-22T01:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:be9f999dd32656d4a4b60bc87a47c0dda6c1d38200e36d0444eebe583b3e60fb","target":"graph","created_at":"2026-05-22T01:03:32Z","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/2605.21788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VLM) approaches achieve promising results but rely on view-dependent reasoning or implicit representations, limiting spatial consistency and interpretability for compositional queries. We propose SceneGraphGrounder, a framework that reformulates 3D grounding as structured graph matching over a reconstructed 3D scene graph. To enable this formulation, we introduce a visual marker prompting strategy that enables a VLM to infer object-object relatio","authors_text":"Brendan Crowe, Christoffer Heckman, Doncey Albin, Xuefei Sun, Xujia Zhang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:30:51Z","title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21788","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":"sha256:68f4edfacc43f935ca695c44fa37472fa091964f547da66691641fb89a2243db","target":"record","created_at":"2026-05-22T01:03:32Z","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":"3679eb95284592a7e57530aa095be18d104340d2541501aa2549e72c22cc9cc1","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:30:51Z","title_canon_sha256":"29e5f99aa779767fc76481df8a112687199659d4a425010f26053ef62f12c660"},"schema_version":"1.0","source":{"id":"2605.21788","kind":"arxiv","version":1}},"canonical_sha256":"22396bf218072f501e9f74543e3719715f09f4ca76993c1cfbb619a3dfcfd03e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22396bf218072f501e9f74543e3719715f09f4ca76993c1cfbb619a3dfcfd03e","first_computed_at":"2026-05-22T01:03:32.470159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:32.470159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"deiZA7MzSDX9cDVCWeLNjUQoW/BQaD7p/72b7HKHis+vDZvaKD6llXpk53nKnMzsox052yoJQLM6S6BquaekAA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:32.470826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68f4edfacc43f935ca695c44fa37472fa091964f547da66691641fb89a2243db","sha256:be9f999dd32656d4a4b60bc87a47c0dda6c1d38200e36d0444eebe583b3e60fb"],"state_sha256":"bad733fa813021d6ce25db2b0433755a3bf77acc79c074c9142f22fef7a68576"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWMMLju2xK2o+g+uGYhVxVz6CSs4wnwUE+AXg73T9yeZHe1RmUBWyHEOy+YRpbMxiQm2wPmVkokSx9xlgQenBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T04:53:10.485017Z","bundle_sha256":"5666a2ed4d53ada783a53025d4f5c07a6e4a374e725f7c5ff3cc6db96829c41b"}}