{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BY5ENMHMU33RX7RAVCCVXGVSZU","short_pith_number":"pith:BY5ENMHM","canonical_record":{"source":{"id":"2412.14171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"3139208067f1984a077d0183513fa153b33c1a95940c0febe9f9c6dfda7e9b77","abstract_canon_sha256":"c0b08d0db958eccefed1a4a70839bbb28797d599f952e5ab21f6c7ba12a54183"},"schema_version":"1.0"},"canonical_sha256":"0e3a46b0eca6f71bfe20a8855b9ab2cd08d9a75dab9d31de97fddc30d9ced46c","source":{"kind":"arxiv","id":"2412.14171","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14171","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14171v2","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14171","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"pith_short_12","alias_value":"BY5ENMHMU33R","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"pith_short_16","alias_value":"BY5ENMHMU33RX7RA","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"pith_short_8","alias_value":"BY5ENMHM","created_at":"2026-05-22T09:22:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BY5ENMHMU33RX7RAVCCVXGVSZU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"3139208067f1984a077d0183513fa153b33c1a95940c0febe9f9c6dfda7e9b77","abstract_canon_sha256":"c0b08d0db958eccefed1a4a70839bbb28797d599f952e5ab21f6c7ba12a54183"},"schema_version":"1.0"},"canonical_sha256":"0e3a46b0eca6f71bfe20a8855b9ab2cd08d9a75dab9d31de97fddc30d9ced46c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T09:22:37.130500Z","signature_b64":"sQ1lFGdzdkOPE6DverQeneKV5FCgvfOHMEELE7jCd41oQZOv97WCEyhfQS1B7sYm+ssNC0xvivInk3myZBgyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e3a46b0eca6f71bfe20a8855b9ab2cd08d9a75dab9d31de97fddc30d9ced46c","last_reissued_at":"2026-05-22T09:22:37.127517Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T09:22:37.127517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14171","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T09:22:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQKzQsMqyYHoVzTpMU1SeOMBEStO9X/zkMl/o4NTtC/e3Y6wzBuVs6+fLVynHIXdXRUnTJKvZ3M5eblu21ftBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T14:13:02.951625Z"},"content_sha256":"205f41b0544eca08ebd93d15438102158d990276e60183b0d800a816488aeaac","schema_version":"1.0","event_id":"sha256:205f41b0544eca08ebd93d15438102158d990276e60183b0d800a816488aeaac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BY5ENMHMU33RX7RAVCCVXGVSZU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anjali W. Gupta, Jihan Yang, Li Fei-Fei, Rilyn Han, Saining Xie, Shusheng Yang","submitted_at":"2024-12-18T18:59:54Z","abstract_excerpt":"Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space'' from videos? We present a novel video-based visual-spatial intelligence benchmark (VSI-Bench) of over 5,000 question-answer pairs, and find that MLLMs exhibit competitive - though subhuman - visual-spatial intelligence. We probe models to express how they think in space both linguistically and visually and find that while spatial reasoning capabilities remain the primary bottl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14171","kind":"arxiv","version":2},"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/2412.14171/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":"2026-05-22T09:22:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YMC7GWIdKrgPtf+gKOPeR2aYB6aQGSJbu3Pa/QGPj2HQz3DnFHap0tmLXKy9gN3S2EjPpGg2nFn1PAZzNqweAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T14:13:02.952113Z"},"content_sha256":"a3c71b7b4fa80a5bf024112ebe9c21036170a07054e141d2f415c3e342d0abb8","schema_version":"1.0","event_id":"sha256:a3c71b7b4fa80a5bf024112ebe9c21036170a07054e141d2f415c3e342d0abb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BY5ENMHMU33RX7RAVCCVXGVSZU/bundle.json","state_url":"https://pith.science/pith/BY5ENMHMU33RX7RAVCCVXGVSZU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BY5ENMHMU33RX7RAVCCVXGVSZU/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":"2026-05-23T14:13:02Z","links":{"resolver":"https://pith.science/pith/BY5ENMHMU33RX7RAVCCVXGVSZU","bundle":"https://pith.science/pith/BY5ENMHMU33RX7RAVCCVXGVSZU/bundle.json","state":"https://pith.science/pith/BY5ENMHMU33RX7RAVCCVXGVSZU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BY5ENMHMU33RX7RAVCCVXGVSZU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BY5ENMHMU33RX7RAVCCVXGVSZU","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":"c0b08d0db958eccefed1a4a70839bbb28797d599f952e5ab21f6c7ba12a54183","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:59:54Z","title_canon_sha256":"3139208067f1984a077d0183513fa153b33c1a95940c0febe9f9c6dfda7e9b77"},"schema_version":"1.0","source":{"id":"2412.14171","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14171","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14171v2","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14171","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"pith_short_12","alias_value":"BY5ENMHMU33R","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"pith_short_16","alias_value":"BY5ENMHMU33RX7RA","created_at":"2026-05-22T09:22:37Z"},{"alias_kind":"pith_short_8","alias_value":"BY5ENMHM","created_at":"2026-05-22T09:22:37Z"}],"graph_snapshots":[{"event_id":"sha256:a3c71b7b4fa80a5bf024112ebe9c21036170a07054e141d2f415c3e342d0abb8","target":"graph","created_at":"2026-05-22T09:22:37Z","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/2412.14171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space'' from videos? We present a novel video-based visual-spatial intelligence benchmark (VSI-Bench) of over 5,000 question-answer pairs, and find that MLLMs exhibit competitive - though subhuman - visual-spatial intelligence. We probe models to express how they think in space both linguistically and visually and find that while spatial reasoning capabilities remain the primary bottl","authors_text":"Anjali W. Gupta, Jihan Yang, Li Fei-Fei, Rilyn Han, Saining Xie, Shusheng Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:59:54Z","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14171","kind":"arxiv","version":2},"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":"sha256:205f41b0544eca08ebd93d15438102158d990276e60183b0d800a816488aeaac","target":"record","created_at":"2026-05-22T09:22:37Z","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":"c0b08d0db958eccefed1a4a70839bbb28797d599f952e5ab21f6c7ba12a54183","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:59:54Z","title_canon_sha256":"3139208067f1984a077d0183513fa153b33c1a95940c0febe9f9c6dfda7e9b77"},"schema_version":"1.0","source":{"id":"2412.14171","kind":"arxiv","version":2}},"canonical_sha256":"0e3a46b0eca6f71bfe20a8855b9ab2cd08d9a75dab9d31de97fddc30d9ced46c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e3a46b0eca6f71bfe20a8855b9ab2cd08d9a75dab9d31de97fddc30d9ced46c","first_computed_at":"2026-05-22T09:22:37.127517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T09:22:37.127517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sQ1lFGdzdkOPE6DverQeneKV5FCgvfOHMEELE7jCd41oQZOv97WCEyhfQS1B7sYm+ssNC0xvivInk3myZBgyBA==","signature_status":"signed_v1","signed_at":"2026-05-22T09:22:37.130500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14171","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:205f41b0544eca08ebd93d15438102158d990276e60183b0d800a816488aeaac","sha256:a3c71b7b4fa80a5bf024112ebe9c21036170a07054e141d2f415c3e342d0abb8"],"state_sha256":"16fc2580b4151fa854337f81fbab3c941988ed2ebb61e3fb283e42dbc9ce5846"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gny7d1s9eXPtrboRa2Lo1Mb5fcmeDwt9iqhYjuoD+fh+yTZCcAaH27unNSKNQdfhzs8E8yZFf+CxNkCuloWBDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T14:13:02.955127Z","bundle_sha256":"cec4d936944a586324ca39e71176920692cac239fbd8a93c44e9db412b3406d8"}}