{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QBUSGPPT3Y2ZDMAY6PYAV7P3SA","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":"9f5c68723bc17cd4b62187ccd408a8ed5ebfae74a1b119d9bfe1204bfdd7cc81","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T15:11:11Z","title_canon_sha256":"9878dce7df006b1ee104b9bf9936d21918c87ea0f4548e71e2878ef9174aad2a"},"schema_version":"1.0","source":{"id":"2504.00883","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00883","created_at":"2026-07-05T10:49:16Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00883v2","created_at":"2026-07-05T10:49:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00883","created_at":"2026-07-05T10:49:16Z"},{"alias_kind":"pith_short_12","alias_value":"QBUSGPPT3Y2Z","created_at":"2026-07-05T10:49:16Z"},{"alias_kind":"pith_short_16","alias_value":"QBUSGPPT3Y2ZDMAY","created_at":"2026-07-05T10:49:16Z"},{"alias_kind":"pith_short_8","alias_value":"QBUSGPPT","created_at":"2026-07-05T10:49:16Z"}],"graph_snapshots":[{"event_id":"sha256:805d2d186784b216811df33e470b57ee0318728999b758e830ffacb245905e8e","target":"graph","created_at":"2026-07-05T10:49:16Z","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/2504.00883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Increasing attention has been placed on improving the reasoning capacities of multi-modal large language models (MLLMs). As the cornerstone for AI agents that function in the physical realm, video-based visual-spatial intelligence (VSI) emerges as one of the most pivotal reasoning capabilities of MLLMs. This work conducts a first, in-depth study on improving the visual-spatial reasoning of MLLMs via R1-Zero-like training. Technically, we first identify that the visual-spatial reasoning capacities of small- to medium-sized Qwen2-VL models cannot be activated via Chain of Thought (CoT) prompts. ","authors_text":"Haonan Lu, Qingsong Xie, Yanhao Zhang, Zhenyi Liao, Zhenyu Yang, Zhijie Deng, Zijian Kong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T15:11:11Z","title":"Improved Visual-Spatial Reasoning via R1-Zero-Like Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00883","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":"sha256:78876141c2470bec942c6fc39e4989365e183bd4a14889b596f82a2aa03d12e7","target":"record","created_at":"2026-07-05T10:49:16Z","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":"9f5c68723bc17cd4b62187ccd408a8ed5ebfae74a1b119d9bfe1204bfdd7cc81","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T15:11:11Z","title_canon_sha256":"9878dce7df006b1ee104b9bf9936d21918c87ea0f4548e71e2878ef9174aad2a"},"schema_version":"1.0","source":{"id":"2504.00883","kind":"arxiv","version":2}},"canonical_sha256":"8069233df3de3591b018f3f00afdfb9006498e0b9f2c5856210f3f2812bfb9a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8069233df3de3591b018f3f00afdfb9006498e0b9f2c5856210f3f2812bfb9a1","first_computed_at":"2026-07-05T10:49:16.245262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:16.245262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UFjvsqFPHSCZ51/Hz4aQf4a2zVYAIfF3RteXF7LF1FN+oH6x3ym/vne7neTuu+javs8H8NZhWR3tFIPJprDaAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:16.245742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00883","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78876141c2470bec942c6fc39e4989365e183bd4a14889b596f82a2aa03d12e7","sha256:805d2d186784b216811df33e470b57ee0318728999b758e830ffacb245905e8e"],"state_sha256":"d05660371c336d9aaa52bb37a27cc4274b017702971e86137da4cc16e7f2b8f2"}