{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5XKNML4SBFWJHVPCTD7TAUHIQU","short_pith_number":"pith:5XKNML4S","canonical_record":{"source":{"id":"2406.07113","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T09:57:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f318bbfb8cc34a621688a385a5d4f36d994d20a0246b5955ffac47e6267c7d06","abstract_canon_sha256":"a6aca4875d171ba4f0ca68260cf7e6512a98d9be66018c72bf0ebfec1cc683a2"},"schema_version":"1.0"},"canonical_sha256":"edd4d62f92096c93d5e298ff3050e88528482bd8306d10164c83fd093ef0618e","source":{"kind":"arxiv","id":"2406.07113","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07113","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07113v4","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07113","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"pith_short_12","alias_value":"5XKNML4SBFWJ","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"pith_short_16","alias_value":"5XKNML4SBFWJHVPC","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"pith_short_8","alias_value":"5XKNML4S","created_at":"2026-07-05T10:59:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5XKNML4SBFWJHVPCTD7TAUHIQU","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07113","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T09:57:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f318bbfb8cc34a621688a385a5d4f36d994d20a0246b5955ffac47e6267c7d06","abstract_canon_sha256":"a6aca4875d171ba4f0ca68260cf7e6512a98d9be66018c72bf0ebfec1cc683a2"},"schema_version":"1.0"},"canonical_sha256":"edd4d62f92096c93d5e298ff3050e88528482bd8306d10164c83fd093ef0618e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:00.779402Z","signature_b64":"I+C2tPN7aFOdZaYEKpOui38N16phgghtO/i2TNZfbShiuMxDRy+feJhkVqc07SOBR2NGm3LMdvdDAn0axL3KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edd4d62f92096c93d5e298ff3050e88528482bd8306d10164c83fd093ef0618e","last_reissued_at":"2026-07-05T10:59:00.778909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:00.778909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07113","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:59:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oOvoxEaSMypDrNWQxEkhnZAmh28d2Eq/9rCrUrM3eytClq4pUHoTc9u3/hjxHqi+QRx8f1ddm35r1vTYw5fjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:59:26.801379Z"},"content_sha256":"cf5429a8185489c0bede721f9b7451423050e82441cda5acb2158af126f6ad9b","schema_version":"1.0","event_id":"sha256:cf5429a8185489c0bede721f9b7451423050e82441cda5acb2158af126f6ad9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5XKNML4SBFWJHVPCTD7TAUHIQU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aleksei Valenkov, Dmitry Yudin, Maxim Monastyrny, Roman Titkov, Sergey Linok, Svetlana Ladanova, Tatiana Zemskova","submitted_at":"2024-06-11T09:57:04Z","abstract_excerpt":"Locating objects described in natural language presents a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object grounding with simple (bare) queries, but cannot cope with ambiguous descriptions that demand an understanding of object relations. To tackle this problem, we propose a modular approach called BBQ (Beyond Bare Queries), which constructs 3D scene graph representation with metric and semantic spatial edges and utilizes a large language model as a human-to-agent interface through our deductive scene reasoning algorithm. B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07113","kind":"arxiv","version":4},"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/2406.07113/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":"2026-07-05T10:59:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/CZsAgZ91Yl26bBQ35St8mRwNAZmdo5SO7/tyrbjVmhIqXsIf6LtrDzSF3AhLASMSS4DgTEZIyyCthG+JoxyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:59:26.801911Z"},"content_sha256":"492aa6a728ef2c48b61c98a1be8397a31b59a153fddfd38f3c656b5e91010a4e","schema_version":"1.0","event_id":"sha256:492aa6a728ef2c48b61c98a1be8397a31b59a153fddfd38f3c656b5e91010a4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/bundle.json","state_url":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/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":"2026-08-10T03:59:26Z","links":{"resolver":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU","bundle":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/bundle.json","state":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5XKNML4SBFWJHVPCTD7TAUHIQU","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":"a6aca4875d171ba4f0ca68260cf7e6512a98d9be66018c72bf0ebfec1cc683a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T09:57:04Z","title_canon_sha256":"f318bbfb8cc34a621688a385a5d4f36d994d20a0246b5955ffac47e6267c7d06"},"schema_version":"1.0","source":{"id":"2406.07113","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07113","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07113v4","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07113","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"pith_short_12","alias_value":"5XKNML4SBFWJ","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"pith_short_16","alias_value":"5XKNML4SBFWJHVPC","created_at":"2026-07-05T10:59:00Z"},{"alias_kind":"pith_short_8","alias_value":"5XKNML4S","created_at":"2026-07-05T10:59:00Z"}],"graph_snapshots":[{"event_id":"sha256:492aa6a728ef2c48b61c98a1be8397a31b59a153fddfd38f3c656b5e91010a4e","target":"graph","created_at":"2026-07-05T10:59:00Z","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/2406.07113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Locating objects described in natural language presents a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object grounding with simple (bare) queries, but cannot cope with ambiguous descriptions that demand an understanding of object relations. To tackle this problem, we propose a modular approach called BBQ (Beyond Bare Queries), which constructs 3D scene graph representation with metric and semantic spatial edges and utilizes a large language model as a human-to-agent interface through our deductive scene reasoning algorithm. B","authors_text":"Aleksei Valenkov, Dmitry Yudin, Maxim Monastyrny, Roman Titkov, Sergey Linok, Svetlana Ladanova, Tatiana Zemskova","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T09:57:04Z","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07113","kind":"arxiv","version":4},"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:cf5429a8185489c0bede721f9b7451423050e82441cda5acb2158af126f6ad9b","target":"record","created_at":"2026-07-05T10:59:00Z","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":"a6aca4875d171ba4f0ca68260cf7e6512a98d9be66018c72bf0ebfec1cc683a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T09:57:04Z","title_canon_sha256":"f318bbfb8cc34a621688a385a5d4f36d994d20a0246b5955ffac47e6267c7d06"},"schema_version":"1.0","source":{"id":"2406.07113","kind":"arxiv","version":4}},"canonical_sha256":"edd4d62f92096c93d5e298ff3050e88528482bd8306d10164c83fd093ef0618e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edd4d62f92096c93d5e298ff3050e88528482bd8306d10164c83fd093ef0618e","first_computed_at":"2026-07-05T10:59:00.778909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:00.778909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I+C2tPN7aFOdZaYEKpOui38N16phgghtO/i2TNZfbShiuMxDRy+feJhkVqc07SOBR2NGm3LMdvdDAn0axL3KDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:00.779402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07113","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf5429a8185489c0bede721f9b7451423050e82441cda5acb2158af126f6ad9b","sha256:492aa6a728ef2c48b61c98a1be8397a31b59a153fddfd38f3c656b5e91010a4e"],"state_sha256":"4f01226c45c37c9798dbf6b2dce9f2eb825a25517626421c47e3bc3b53d857f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yfeJ52UNFfFtZjX1kXbHqectjoEJXA5fLSQfhy8YDmI41XoPFv7So/99eF25/xWcNiVm/VYvK92HPT7PFuolBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:59:26.810011Z","bundle_sha256":"f0ecc67a8907f3a4b9083bae29860c06b24095318dd7060fc60575a0981a85d2"}}