{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GQ4LX5SKKYOQHF2BFT62VYUCCP","short_pith_number":"pith:GQ4LX5SK","canonical_record":{"source":{"id":"2411.06048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-09T03:07:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b52b76a0f177b9f6411afbc2fb608ba55ee9cb5fec1efd0c36e70c4926867fe5","abstract_canon_sha256":"63e0ef1e3b19c2e8b3b026322c9033597d656981da003f8de2263e747bcd3eb0"},"schema_version":"1.0"},"canonical_sha256":"3438bbf64a561d0397412cfdaae28213ddbf7f6938914476e6ae2f15708869cc","source":{"kind":"arxiv","id":"2411.06048","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06048","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06048v1","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06048","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"pith_short_12","alias_value":"GQ4LX5SKKYOQ","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"GQ4LX5SKKYOQHF2B","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"GQ4LX5SK","created_at":"2026-07-05T09:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GQ4LX5SKKYOQHF2BFT62VYUCCP","target":"record","payload":{"canonical_record":{"source":{"id":"2411.06048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-09T03:07:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b52b76a0f177b9f6411afbc2fb608ba55ee9cb5fec1efd0c36e70c4926867fe5","abstract_canon_sha256":"63e0ef1e3b19c2e8b3b026322c9033597d656981da003f8de2263e747bcd3eb0"},"schema_version":"1.0"},"canonical_sha256":"3438bbf64a561d0397412cfdaae28213ddbf7f6938914476e6ae2f15708869cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:15.640978Z","signature_b64":"Ai0i1AkBj7wnnZNeJ3rF1grTKz7lyqppCbM6RcihhtC6SSBQCN5MpIPCvAUfF3HJN4wEm8jeJ1OmwGivbQscDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3438bbf64a561d0397412cfdaae28213ddbf7f6938914476e6ae2f15708869cc","last_reissued_at":"2026-07-05T09:33:15.640310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:15.640310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.06048","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":"2026-07-05T09:33:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9rtyEBGQnq8aUfdFZ2+NjZqJifiSA5BE58R5ZatKGz+5yHfxSok5ywyqaPjeIJVoVrrslLv90chaV52PGvsxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:45:52.723194Z"},"content_sha256":"ecefb2c89b53204206f414388f98a0f6b22f34e1e505943a966e35eb6428092c","schema_version":"1.0","event_id":"sha256:ecefb2c89b53204206f414388f98a0f6b22f34e1e505943a966e35eb6428092c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GQ4LX5SKKYOQHF2BFT62VYUCCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fatemeh Shiri, Gholamreza Haffari, Mona Golestan Far, Xiao-Yu Guo, Xin Yu, Yuan-Fang Li","submitted_at":"2024-11-09T03:07:33Z","abstract_excerpt":"Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs' spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs' spatial reasoning. Secondly, LMMs struggle more with questions posed from the human persp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06048","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/2411.06048/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":"2026-07-05T09:33:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lUPUL8C7mnMKs+kZAzCP+ngta/niabb8izyRF7F5/t99Nas2kmUwPavDGLi0f06oDzwHQ3aeiP96he3p4TVbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:45:52.724128Z"},"content_sha256":"1ee8523ffc68eccaaa773d2e3a6b60b399387cc8838adeb28540bddac187af22","schema_version":"1.0","event_id":"sha256:1ee8523ffc68eccaaa773d2e3a6b60b399387cc8838adeb28540bddac187af22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQ4LX5SKKYOQHF2BFT62VYUCCP/bundle.json","state_url":"https://pith.science/pith/GQ4LX5SKKYOQHF2BFT62VYUCCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQ4LX5SKKYOQHF2BFT62VYUCCP/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":"2026-08-13T20:45:52Z","links":{"resolver":"https://pith.science/pith/GQ4LX5SKKYOQHF2BFT62VYUCCP","bundle":"https://pith.science/pith/GQ4LX5SKKYOQHF2BFT62VYUCCP/bundle.json","state":"https://pith.science/pith/GQ4LX5SKKYOQHF2BFT62VYUCCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQ4LX5SKKYOQHF2BFT62VYUCCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GQ4LX5SKKYOQHF2BFT62VYUCCP","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":"63e0ef1e3b19c2e8b3b026322c9033597d656981da003f8de2263e747bcd3eb0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-09T03:07:33Z","title_canon_sha256":"b52b76a0f177b9f6411afbc2fb608ba55ee9cb5fec1efd0c36e70c4926867fe5"},"schema_version":"1.0","source":{"id":"2411.06048","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06048","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06048v1","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06048","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"pith_short_12","alias_value":"GQ4LX5SKKYOQ","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"GQ4LX5SKKYOQHF2B","created_at":"2026-07-05T09:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"GQ4LX5SK","created_at":"2026-07-05T09:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:1ee8523ffc68eccaaa773d2e3a6b60b399387cc8838adeb28540bddac187af22","target":"graph","created_at":"2026-07-05T09:33:15Z","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/2411.06048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs' spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs' spatial reasoning. Secondly, LMMs struggle more with questions posed from the human persp","authors_text":"Fatemeh Shiri, Gholamreza Haffari, Mona Golestan Far, Xiao-Yu Guo, Xin Yu, Yuan-Fang Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-09T03:07:33Z","title":"An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06048","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:ecefb2c89b53204206f414388f98a0f6b22f34e1e505943a966e35eb6428092c","target":"record","created_at":"2026-07-05T09:33:15Z","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":"63e0ef1e3b19c2e8b3b026322c9033597d656981da003f8de2263e747bcd3eb0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-09T03:07:33Z","title_canon_sha256":"b52b76a0f177b9f6411afbc2fb608ba55ee9cb5fec1efd0c36e70c4926867fe5"},"schema_version":"1.0","source":{"id":"2411.06048","kind":"arxiv","version":1}},"canonical_sha256":"3438bbf64a561d0397412cfdaae28213ddbf7f6938914476e6ae2f15708869cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3438bbf64a561d0397412cfdaae28213ddbf7f6938914476e6ae2f15708869cc","first_computed_at":"2026-07-05T09:33:15.640310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:15.640310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ai0i1AkBj7wnnZNeJ3rF1grTKz7lyqppCbM6RcihhtC6SSBQCN5MpIPCvAUfF3HJN4wEm8jeJ1OmwGivbQscDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:15.640978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06048","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecefb2c89b53204206f414388f98a0f6b22f34e1e505943a966e35eb6428092c","sha256:1ee8523ffc68eccaaa773d2e3a6b60b399387cc8838adeb28540bddac187af22"],"state_sha256":"8e83f7c55239cc22f857b0bdf5c721acda3071e602f4f8b8b5f6fdbb526f352a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E/lhancLKFq6PtDFVI69Ugnwz+55l2lEbXgMFhCHH/68Fzm0hrn5yOTtbPtMrIWzZ8I9lX8PADICTacZl/cYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T20:45:52.748642Z","bundle_sha256":"8fce72c16f8c353adca4214839d0a9ce2211fe40ff89d7370b9b491663297e7e"}}