{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AOLPNEOFDD7F73MPKXQWTFIGP2","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":"02959976ed56cc2d03bf151155b21dfe3ef315209a3c9f1aaaa51786686b0516","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T00:34:45Z","title_canon_sha256":"04853704a1915551209d3cf36a733d197d23b9495297b8b8d48c5d4ba83d4040"},"schema_version":"1.0","source":{"id":"2505.21850","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21850","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21850v2","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21850","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"AOLPNEOFDD7F","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_16","alias_value":"AOLPNEOFDD7F73MP","created_at":"2026-07-05T11:12:33Z"},{"alias_kind":"pith_short_8","alias_value":"AOLPNEOF","created_at":"2026-07-05T11:12:33Z"}],"graph_snapshots":[{"event_id":"sha256:cc344aa121104cd2a5f8b6938b0c8be0bfa7465a303a2953b42458537fa2e775","target":"graph","created_at":"2026-07-05T11:12:33Z","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/2505.21850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Multimodal Large Language Models (MLLMs) excel in general visual reasoning but remain underexplored in Abstract Visual Reasoning (AVR), which demands higher-order reasoning to identify abstract rules beyond simple perception. Existing AVR benchmarks focus on single-step reasoning, emphasizing the end result but neglecting the multi-stage nature of reasoning process. Past studies found MLLMs struggle with these benchmarks, but it doesn't explain how they fail. To address this gap, we introduce MultiStAR, a Multi-Stage AVR benchmark, based on RAVEN, designed to assess reasoning across va","authors_text":"Chao Lei, Jey Han Lau, Jiayang Ao, Krista A. Ehinger, Yanbei Jiang, Yihao Ding","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T00:34:45Z","title":"Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21850","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:bd65ba75bb4c42f7a212a6b9ebe5cdcc8bfb969d0d272436abd4c22cc621282e","target":"record","created_at":"2026-07-05T11:12:33Z","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":"02959976ed56cc2d03bf151155b21dfe3ef315209a3c9f1aaaa51786686b0516","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T00:34:45Z","title_canon_sha256":"04853704a1915551209d3cf36a733d197d23b9495297b8b8d48c5d4ba83d4040"},"schema_version":"1.0","source":{"id":"2505.21850","kind":"arxiv","version":2}},"canonical_sha256":"0396f691c518fe5fed8f55e16995067e91ca6de8da368489b40ddb2e9b3af70a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0396f691c518fe5fed8f55e16995067e91ca6de8da368489b40ddb2e9b3af70a","first_computed_at":"2026-07-05T11:12:33.858019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:33.858019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hiRy86vPIGo1IXGsfPmY4B4/uqEwUgxQ6bDprXDYRdiETa92+2B3laV58bZ9seNPZFtLyUva0h2BGTiq/qQwAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:33.858665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21850","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd65ba75bb4c42f7a212a6b9ebe5cdcc8bfb969d0d272436abd4c22cc621282e","sha256:cc344aa121104cd2a5f8b6938b0c8be0bfa7465a303a2953b42458537fa2e775"],"state_sha256":"5375b58f186c0bee59e309a51e7dd258f091053ef556b8642b508ef127be52f9"}