{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RXNDWAJVKCK3RUL26ZSDQ36PGE","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":"1cb802958e82bc8ad49c0e8fee2175c8f23bc7595558ace0fbb1845d9470af00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-21T12:09:13Z","title_canon_sha256":"0fc79b9cc500719006ca63411b365d5952d248c20807c3c676a19f28db4de53d"},"schema_version":"1.0","source":{"id":"2412.16599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16599","created_at":"2026-07-05T09:52:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16599v1","created_at":"2026-07-05T09:52:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16599","created_at":"2026-07-05T09:52:50Z"},{"alias_kind":"pith_short_12","alias_value":"RXNDWAJVKCK3","created_at":"2026-07-05T09:52:50Z"},{"alias_kind":"pith_short_16","alias_value":"RXNDWAJVKCK3RUL2","created_at":"2026-07-05T09:52:50Z"},{"alias_kind":"pith_short_8","alias_value":"RXNDWAJV","created_at":"2026-07-05T09:52:50Z"}],"graph_snapshots":[{"event_id":"sha256:9846663634bfcea627f7332805d99aecc2a34f17ab16844c36a593767c37f020","target":"graph","created_at":"2026-07-05T09:52:50Z","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/2412.16599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direction reasoning is essential for intelligent systems to understand the real world. While existing work focuses primarily on spatial reasoning, compass direction reasoning remains underexplored. To address this, we propose the Compass Direction Reasoning (CDR) benchmark, designed to evaluate the direction reasoning capabilities of multimodal language models (MLMs). CDR includes three types images to test spatial (up, down, left, right) and compass (north, south, east, west) directions. Our evaluation reveals that most MLMs struggle with direction reasoning, often performing at random guessi","authors_text":"Bin Sun, Hang Yin, Kan Li, Xin Liu, Zhifeng Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-21T12:09:13Z","title":"Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16599","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":"sha256:3e34802c7a5605a7c785a269d2d8783cd781d4a8d9d2d6286863c3ee226cfe57","target":"record","created_at":"2026-07-05T09:52:50Z","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":"1cb802958e82bc8ad49c0e8fee2175c8f23bc7595558ace0fbb1845d9470af00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-21T12:09:13Z","title_canon_sha256":"0fc79b9cc500719006ca63411b365d5952d248c20807c3c676a19f28db4de53d"},"schema_version":"1.0","source":{"id":"2412.16599","kind":"arxiv","version":1}},"canonical_sha256":"8dda3b01355095b8d17af664386fcf3102331cc7080a055778a1c8206ff250be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dda3b01355095b8d17af664386fcf3102331cc7080a055778a1c8206ff250be","first_computed_at":"2026-07-05T09:52:50.078694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:50.078694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mOY+HcTAbiGOC21EabD1wncfl6q/9BQC10/wXFmIpnBM3ASBRYkvCQeGLPAr29Ir130WGSolpNHSdOsXy5cGAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:50.079122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e34802c7a5605a7c785a269d2d8783cd781d4a8d9d2d6286863c3ee226cfe57","sha256:9846663634bfcea627f7332805d99aecc2a34f17ab16844c36a593767c37f020"],"state_sha256":"7c844eabd21ab25fe1dac5a1ec4d3da66e1a76a8e45040ae8d945075638ef13e"}