{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VRFWDBJFSROCX5GCJ3ZVSPTDF2","short_pith_number":"pith:VRFWDBJF","canonical_record":{"source":{"id":"2107.03438","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-07T18:55:03Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"c873b639f7f806d302ef3c293bae592e466963a3ad28dc60fbc44385f99860f9","abstract_canon_sha256":"5f47f72b43afd830350bbcd4fd514d1c81243836e088b7d4ddf7c68d45e20d87"},"schema_version":"1.0"},"canonical_sha256":"ac4b618525945c2bf4c24ef3593e632e90833f62a7004ad0b85f0203336dd6db","source":{"kind":"arxiv","id":"2107.03438","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.03438","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"arxiv_version","alias_value":"2107.03438v3","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03438","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"pith_short_12","alias_value":"VRFWDBJFSROC","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"VRFWDBJFSROCX5GC","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"VRFWDBJF","created_at":"2026-07-05T03:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VRFWDBJFSROCX5GCJ3ZVSPTDF2","target":"record","payload":{"canonical_record":{"source":{"id":"2107.03438","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-07T18:55:03Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"c873b639f7f806d302ef3c293bae592e466963a3ad28dc60fbc44385f99860f9","abstract_canon_sha256":"5f47f72b43afd830350bbcd4fd514d1c81243836e088b7d4ddf7c68d45e20d87"},"schema_version":"1.0"},"canonical_sha256":"ac4b618525945c2bf4c24ef3593e632e90833f62a7004ad0b85f0203336dd6db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:17.703504Z","signature_b64":"cviJC5stuJ7yRIzs1S94bw8tKNeYp4XIHCMGiWX74c7f0HTzYRn4/I7cyg7ForRwqWEsioBz+yDfaSPJsK2IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac4b618525945c2bf4c24ef3593e632e90833f62a7004ad0b85f0203336dd6db","last_reissued_at":"2026-07-05T03:29:17.702938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:17.702938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.03438","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:29:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M994uF/fxlVLH1OnD2ZuhWjaaonlqPfBwS374/fMsX5Q+xmqQ85SNxwwhH4MZOc8n67qUYPMKudamN1V5JN6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:05:39.812306Z"},"content_sha256":"8604a3c76cf16f480209ada75fa165e107d333d84d15bdad6f947195c5070f4d","schema_version":"1.0","event_id":"sha256:8604a3c76cf16f480209ada75fa165e107d333d84d15bdad6f947195c5070f4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VRFWDBJFSROCX5GCJ3ZVSPTDF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Ali Farhadi, Dieter Fox, Junha Roh, Karthik Desingh","submitted_at":"2021-07-07T18:55:03Z","abstract_excerpt":"For robots to understand human instructions and perform meaningful tasks in the near future, it is important to develop learned models that comprehend referential language to identify common objects in real-world 3D scenes. In this paper, we introduce a spatial-language model for a 3D visual grounding problem. Specifically, given a reconstructed 3D scene in the form of point clouds with 3D bounding boxes of potential object candidates, and a language utterance referring to a target object in the scene, our model successfully identifies the target object from a set of potential candidates. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03438","kind":"arxiv","version":3},"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/2107.03438/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":"2026-07-05T03:29:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c3spQGYoRqrjDX33eUb9mumbnGyUjXEmk3Y0WBFQoHSQkGKDpzNIuLqQ0d8iEobRjtrar3fV1S3YcEWNZtcqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:05:39.812700Z"},"content_sha256":"e887ad74d3bb453c84f9c4666c9147ab3505712fce4635625f0ab7b813ccd4e2","schema_version":"1.0","event_id":"sha256:e887ad74d3bb453c84f9c4666c9147ab3505712fce4635625f0ab7b813ccd4e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/bundle.json","state_url":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/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":"2026-07-09T02:05:39Z","links":{"resolver":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2","bundle":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/bundle.json","state":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VRFWDBJFSROCX5GCJ3ZVSPTDF2","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":"5f47f72b43afd830350bbcd4fd514d1c81243836e088b7d4ddf7c68d45e20d87","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-07T18:55:03Z","title_canon_sha256":"c873b639f7f806d302ef3c293bae592e466963a3ad28dc60fbc44385f99860f9"},"schema_version":"1.0","source":{"id":"2107.03438","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.03438","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"arxiv_version","alias_value":"2107.03438v3","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03438","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"pith_short_12","alias_value":"VRFWDBJFSROC","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"VRFWDBJFSROCX5GC","created_at":"2026-07-05T03:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"VRFWDBJF","created_at":"2026-07-05T03:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:e887ad74d3bb453c84f9c4666c9147ab3505712fce4635625f0ab7b813ccd4e2","target":"graph","created_at":"2026-07-05T03:29:17Z","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/2107.03438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For robots to understand human instructions and perform meaningful tasks in the near future, it is important to develop learned models that comprehend referential language to identify common objects in real-world 3D scenes. In this paper, we introduce a spatial-language model for a 3D visual grounding problem. Specifically, given a reconstructed 3D scene in the form of point clouds with 3D bounding boxes of potential object candidates, and a language utterance referring to a target object in the scene, our model successfully identifies the target object from a set of potential candidates. Spec","authors_text":"Ali Farhadi, Dieter Fox, Junha Roh, Karthik Desingh","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-07T18:55:03Z","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03438","kind":"arxiv","version":3},"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":"sha256:8604a3c76cf16f480209ada75fa165e107d333d84d15bdad6f947195c5070f4d","target":"record","created_at":"2026-07-05T03:29:17Z","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":"5f47f72b43afd830350bbcd4fd514d1c81243836e088b7d4ddf7c68d45e20d87","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-07T18:55:03Z","title_canon_sha256":"c873b639f7f806d302ef3c293bae592e466963a3ad28dc60fbc44385f99860f9"},"schema_version":"1.0","source":{"id":"2107.03438","kind":"arxiv","version":3}},"canonical_sha256":"ac4b618525945c2bf4c24ef3593e632e90833f62a7004ad0b85f0203336dd6db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac4b618525945c2bf4c24ef3593e632e90833f62a7004ad0b85f0203336dd6db","first_computed_at":"2026-07-05T03:29:17.702938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:17.702938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cviJC5stuJ7yRIzs1S94bw8tKNeYp4XIHCMGiWX74c7f0HTzYRn4/I7cyg7ForRwqWEsioBz+yDfaSPJsK2IBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:17.703504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.03438","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8604a3c76cf16f480209ada75fa165e107d333d84d15bdad6f947195c5070f4d","sha256:e887ad74d3bb453c84f9c4666c9147ab3505712fce4635625f0ab7b813ccd4e2"],"state_sha256":"91622f53699a43997a79a7ba4a28925f6d6d654aef4f0df1b5a5bb4ef3bf2028"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogsmnef/Ejf98x2yOjWPyqNSSWeOxbR5Umk1AcVWNTP5zc7JQ7+SMYOmQtBQ89Ih6cL8DLl8u4Ekcb9s9z3IAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:05:39.814746Z","bundle_sha256":"3628e0efba429695b7945cd01aaba9b3f0e429471ad1201c4a96fd863e906a7d"}}