{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YMQFY4WCM5NYPZRN6W7HIF4V43","short_pith_number":"pith:YMQFY4WC","canonical_record":{"source":{"id":"2606.03100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T03:38:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b690d96eefc7308d70af6685600ffa77d4f2b50c5aff177fe758b13c1f407e5","abstract_canon_sha256":"0a550b3a6620c0eae31e67452e1b615010946f546a3353530e9f078a4deacf16"},"schema_version":"1.0"},"canonical_sha256":"c3205c72c2675b87e62df5be741795e6dd096cc534390996732f877d8c349836","source":{"kind":"arxiv","id":"2606.03100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03100","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03100v1","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03100","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"YMQFY4WCM5NY","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"YMQFY4WCM5NYPZRN","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"YMQFY4WC","created_at":"2026-06-03T01:05:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YMQFY4WCM5NYPZRN6W7HIF4V43","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T03:38:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b690d96eefc7308d70af6685600ffa77d4f2b50c5aff177fe758b13c1f407e5","abstract_canon_sha256":"0a550b3a6620c0eae31e67452e1b615010946f546a3353530e9f078a4deacf16"},"schema_version":"1.0"},"canonical_sha256":"c3205c72c2675b87e62df5be741795e6dd096cc534390996732f877d8c349836","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:31.692306Z","signature_b64":"S77TOrUxBHHshY6d76uwEMSAGQlA6qOMxhA4y8dcBT3/TeFeDYuK8Kw0W0tpy8Wy3xbQS+ZKdVIFc3HYedLNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3205c72c2675b87e62df5be741795e6dd096cc534390996732f877d8c349836","last_reissued_at":"2026-06-03T01:05:31.691948Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:31.691948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03100","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":"2026-06-03T01:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ji/bhBFIamIdwm31bWYlsxvmRMYI+85zvKcyhHwpm2C5v2wk9DD4QuZ4dRV9mojcbrm0vtveB/0r3gkmNMeGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:36:06.868070Z"},"content_sha256":"fb8d8118fa0cb4ab49944291582e6af419b0819f4f9c9b9dc89f063637368952","schema_version":"1.0","event_id":"sha256:fb8d8118fa0cb4ab49944291582e6af419b0819f4f9c9b9dc89f063637368952"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YMQFY4WCM5NYPZRN6W7HIF4V43","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dawei Su, Dongsheng Wang, Hui Huang","submitted_at":"2026-06-02T03:38:51Z","abstract_excerpt":"Recently, zero-shot 3D scene understanding via 2D Vision-Language Models (VLMs) has gained increasing research interest due to their promising spatial reasoning capabilities. Typically, multiple 2D views are sampled from a 3D point cloud and fed into pre-trained VLMs to answer a given question. This paradigm highlights the critical role of input context quality and raises the challenge of retaining as many task-relevant 3D details as possible under a limited input budget. We propose \\texttt{KeyVT}, a hierarchical approach for input context collection at both the view and token levels. Specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03100","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/2606.03100/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":"2026-06-03T01:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kRZ6yeZFS9+q0gp+NeXGvmQbUdWRGk3f/I7KrlE0SLOeyqwqMkzQUX2QoMi+eEEmmhzJavFsLlN9PnPAWSflBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:36:06.868456Z"},"content_sha256":"c61fe74675fa20224ee38059837ce98e4e01380b97c7e5bd1083cfe690a3d350","schema_version":"1.0","event_id":"sha256:c61fe74675fa20224ee38059837ce98e4e01380b97c7e5bd1083cfe690a3d350"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YMQFY4WCM5NYPZRN6W7HIF4V43/bundle.json","state_url":"https://pith.science/pith/YMQFY4WCM5NYPZRN6W7HIF4V43/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YMQFY4WCM5NYPZRN6W7HIF4V43/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":"2026-06-09T12:36:06Z","links":{"resolver":"https://pith.science/pith/YMQFY4WCM5NYPZRN6W7HIF4V43","bundle":"https://pith.science/pith/YMQFY4WCM5NYPZRN6W7HIF4V43/bundle.json","state":"https://pith.science/pith/YMQFY4WCM5NYPZRN6W7HIF4V43/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YMQFY4WCM5NYPZRN6W7HIF4V43/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YMQFY4WCM5NYPZRN6W7HIF4V43","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":"0a550b3a6620c0eae31e67452e1b615010946f546a3353530e9f078a4deacf16","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T03:38:51Z","title_canon_sha256":"7b690d96eefc7308d70af6685600ffa77d4f2b50c5aff177fe758b13c1f407e5"},"schema_version":"1.0","source":{"id":"2606.03100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03100","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03100v1","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03100","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"YMQFY4WCM5NY","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"YMQFY4WCM5NYPZRN","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"YMQFY4WC","created_at":"2026-06-03T01:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:c61fe74675fa20224ee38059837ce98e4e01380b97c7e5bd1083cfe690a3d350","target":"graph","created_at":"2026-06-03T01:05:31Z","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/2606.03100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, zero-shot 3D scene understanding via 2D Vision-Language Models (VLMs) has gained increasing research interest due to their promising spatial reasoning capabilities. Typically, multiple 2D views are sampled from a 3D point cloud and fed into pre-trained VLMs to answer a given question. This paradigm highlights the critical role of input context quality and raises the challenge of retaining as many task-relevant 3D details as possible under a limited input budget. We propose \\texttt{KeyVT}, a hierarchical approach for input context collection at both the view and token levels. Specific","authors_text":"Dawei Su, Dongsheng Wang, Hui Huang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T03:38:51Z","title":"Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03100","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:fb8d8118fa0cb4ab49944291582e6af419b0819f4f9c9b9dc89f063637368952","target":"record","created_at":"2026-06-03T01:05:31Z","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":"0a550b3a6620c0eae31e67452e1b615010946f546a3353530e9f078a4deacf16","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T03:38:51Z","title_canon_sha256":"7b690d96eefc7308d70af6685600ffa77d4f2b50c5aff177fe758b13c1f407e5"},"schema_version":"1.0","source":{"id":"2606.03100","kind":"arxiv","version":1}},"canonical_sha256":"c3205c72c2675b87e62df5be741795e6dd096cc534390996732f877d8c349836","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3205c72c2675b87e62df5be741795e6dd096cc534390996732f877d8c349836","first_computed_at":"2026-06-03T01:05:31.691948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:31.691948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S77TOrUxBHHshY6d76uwEMSAGQlA6qOMxhA4y8dcBT3/TeFeDYuK8Kw0W0tpy8Wy3xbQS+ZKdVIFc3HYedLNBQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:31.692306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb8d8118fa0cb4ab49944291582e6af419b0819f4f9c9b9dc89f063637368952","sha256:c61fe74675fa20224ee38059837ce98e4e01380b97c7e5bd1083cfe690a3d350"],"state_sha256":"c050f2def695f3c333214ed18ced2359445f576846b75789b5c57d174754136f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h4KZP8gXR+fYIavYNW5IAJESTOSBPjJ3sNIzI0J35HHdXBgSqyD9EqonnOA6hz+/FqE5Ns2sbLtAP8dtHRYVBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T12:36:06.870455Z","bundle_sha256":"5507736a1cdf76d90d811ee6cb9976ed531344f899cc03e4f5f7a81eddd6db88"}}