{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MV46K5N6UM3KJKIR3BOSWSPKJJ","short_pith_number":"pith:MV46K5N6","canonical_record":{"source":{"id":"2401.12168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T18:01:01Z","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"68bb85a224eb63bc86b944b887e7e64730e9203fb1a4b1ff8f0b2db7b76e3db4","abstract_canon_sha256":"21ab30f07420e661392af14e6298174bb7400e5a2234a428b86ca00eeeea7101"},"schema_version":"1.0"},"canonical_sha256":"6579e575bea336a4a911d85d2b49ea4a7a60f8bc91e4c1da4660cd699ce141dc","source":{"kind":"arxiv","id":"2401.12168","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12168","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12168v1","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12168","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"pith_short_12","alias_value":"MV46K5N6UM3K","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"pith_short_16","alias_value":"MV46K5N6UM3KJKIR","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"pith_short_8","alias_value":"MV46K5N6","created_at":"2026-07-05T07:36:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MV46K5N6UM3KJKIR3BOSWSPKJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T18:01:01Z","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"68bb85a224eb63bc86b944b887e7e64730e9203fb1a4b1ff8f0b2db7b76e3db4","abstract_canon_sha256":"21ab30f07420e661392af14e6298174bb7400e5a2234a428b86ca00eeeea7101"},"schema_version":"1.0"},"canonical_sha256":"6579e575bea336a4a911d85d2b49ea4a7a60f8bc91e4c1da4660cd699ce141dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:16.363307Z","signature_b64":"URQOfD/Ag9HhAD1WVdY15u3SwKG0/I7n2dQ6MTcIyX6cp7dQnYSNcl5Vdid11iX7m+yscCxzfUyj7RLDve1bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6579e575bea336a4a911d85d2b49ea4a7a60f8bc91e4c1da4660cd699ce141dc","last_reissued_at":"2026-07-05T07:36:16.362868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:16.362868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12168","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":"2026-07-05T07:36:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzlSF1KuaiZieTKWQ/dVzPCO5EbVd+pqvPb1pB1slWj+7pDz08B1moCEOaOiiS6NutHRSJxySU2q3MkE/iOgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:30:56.575244Z"},"content_sha256":"13a5c3c127889d4de0272f34f86dce98fdc9344ea7ef3c915e5d296f8289de73","schema_version":"1.0","event_id":"sha256:13a5c3c127889d4de0272f34f86dce98fdc9344ea7ef3c915e5d296f8289de73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MV46K5N6UM3KJKIR3BOSWSPKJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Boyuan Chen, Brian Ichter, Danny Driess, Dorsa Sadigh, Fei Xia, Leonidas Guibas, Pete Florence, Sean Kirmani, Zhuo Xu","submitted_at":"2024-01-22T18:01:01Z","abstract_excerpt":"Understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. While Vision Language Models (VLM) have demonstrated remarkable performance in certain VQA benchmarks, they still lack capabilities in 3D spatial reasoning, such as recognizing quantitative relationships of physical objects like distances or size differences. We hypothesize that VLMs' limited spatial reasoning capability is due to the lack of 3D spatial knowledge in training data and aim to solve this problem by training VLMs with Internet-scale spatial reasonin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12168","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/2401.12168/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":"2026-07-05T07:36:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fqdH5a3LvFFEO/Bq1D4zOd+9NFHJGDFcsY52twY6DOI2F8JZUBsVquZ+JJaTeLL87+cVNmVhhX5ZAzDDYwXjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:30:56.576277Z"},"content_sha256":"13c8e1b8444bc56ebf813390e4bd483443b46f4fd1a797e47fcab3c24fa76982","schema_version":"1.0","event_id":"sha256:13c8e1b8444bc56ebf813390e4bd483443b46f4fd1a797e47fcab3c24fa76982"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MV46K5N6UM3KJKIR3BOSWSPKJJ/bundle.json","state_url":"https://pith.science/pith/MV46K5N6UM3KJKIR3BOSWSPKJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MV46K5N6UM3KJKIR3BOSWSPKJJ/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":"2026-08-03T16:30:56Z","links":{"resolver":"https://pith.science/pith/MV46K5N6UM3KJKIR3BOSWSPKJJ","bundle":"https://pith.science/pith/MV46K5N6UM3KJKIR3BOSWSPKJJ/bundle.json","state":"https://pith.science/pith/MV46K5N6UM3KJKIR3BOSWSPKJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MV46K5N6UM3KJKIR3BOSWSPKJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MV46K5N6UM3KJKIR3BOSWSPKJJ","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":"21ab30f07420e661392af14e6298174bb7400e5a2234a428b86ca00eeeea7101","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T18:01:01Z","title_canon_sha256":"68bb85a224eb63bc86b944b887e7e64730e9203fb1a4b1ff8f0b2db7b76e3db4"},"schema_version":"1.0","source":{"id":"2401.12168","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12168","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12168v1","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12168","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"pith_short_12","alias_value":"MV46K5N6UM3K","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"pith_short_16","alias_value":"MV46K5N6UM3KJKIR","created_at":"2026-07-05T07:36:16Z"},{"alias_kind":"pith_short_8","alias_value":"MV46K5N6","created_at":"2026-07-05T07:36:16Z"}],"graph_snapshots":[{"event_id":"sha256:13c8e1b8444bc56ebf813390e4bd483443b46f4fd1a797e47fcab3c24fa76982","target":"graph","created_at":"2026-07-05T07:36:16Z","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/2401.12168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. While Vision Language Models (VLM) have demonstrated remarkable performance in certain VQA benchmarks, they still lack capabilities in 3D spatial reasoning, such as recognizing quantitative relationships of physical objects like distances or size differences. We hypothesize that VLMs' limited spatial reasoning capability is due to the lack of 3D spatial knowledge in training data and aim to solve this problem by training VLMs with Internet-scale spatial reasonin","authors_text":"Boyuan Chen, Brian Ichter, Danny Driess, Dorsa Sadigh, Fei Xia, Leonidas Guibas, Pete Florence, Sean Kirmani, Zhuo Xu","cross_cats":["cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T18:01:01Z","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12168","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":"sha256:13a5c3c127889d4de0272f34f86dce98fdc9344ea7ef3c915e5d296f8289de73","target":"record","created_at":"2026-07-05T07:36:16Z","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":"21ab30f07420e661392af14e6298174bb7400e5a2234a428b86ca00eeeea7101","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T18:01:01Z","title_canon_sha256":"68bb85a224eb63bc86b944b887e7e64730e9203fb1a4b1ff8f0b2db7b76e3db4"},"schema_version":"1.0","source":{"id":"2401.12168","kind":"arxiv","version":1}},"canonical_sha256":"6579e575bea336a4a911d85d2b49ea4a7a60f8bc91e4c1da4660cd699ce141dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6579e575bea336a4a911d85d2b49ea4a7a60f8bc91e4c1da4660cd699ce141dc","first_computed_at":"2026-07-05T07:36:16.362868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:16.362868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"URQOfD/Ag9HhAD1WVdY15u3SwKG0/I7n2dQ6MTcIyX6cp7dQnYSNcl5Vdid11iX7m+yscCxzfUyj7RLDve1bAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:16.363307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12168","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13a5c3c127889d4de0272f34f86dce98fdc9344ea7ef3c915e5d296f8289de73","sha256:13c8e1b8444bc56ebf813390e4bd483443b46f4fd1a797e47fcab3c24fa76982"],"state_sha256":"c690e0aacbe63d62964eb983ee833dd04d94c723072a09660cbbd4df67fb81f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kGvVG/9CqIZ0VIhPUlC9AflyjhHNTDG4DMnFmOqyMR2JpbXiRdSMjBps+m6fTLAJI+p/ZbGgk8p7AMdjn/vaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:30:56.583629Z","bundle_sha256":"48e26fe3544ec5a54596cdcbafbe7ee5fbb43494e8298a44eb9a614e39bfb4e0"}}