{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D5HJLOWA4BESQBFAEMZDKI3262","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":"6cb8ce9a5784ea7cec87340921c586478c496ff7e5df436d0be6320b164fe601","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T03:18:24Z","title_canon_sha256":"76dcd2611cfbe7ddaff6aab49f57bde8b846035438a17927a7a7a8be19301cbb"},"schema_version":"1.0","source":{"id":"2504.01324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01324","created_at":"2026-07-05T10:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01324v1","created_at":"2026-07-05T10:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01324","created_at":"2026-07-05T10:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"D5HJLOWA4BES","created_at":"2026-07-05T10:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"D5HJLOWA4BESQBFA","created_at":"2026-07-05T10:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"D5HJLOWA","created_at":"2026-07-05T10:43:12Z"}],"graph_snapshots":[{"event_id":"sha256:d8e9bac2ab932709b21411ae19434fbf57952b73513dc8c15fc9a56c99fdf254","target":"graph","created_at":"2026-07-05T10:43:12Z","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/2504.01324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper is a pioneering work attempting to address abstract visual reasoning (AVR) problems for large vision-language models (VLMs). We make a common LLaVA-NeXT 7B model capable of perceiving and reasoning about specific AVR problems, surpassing both open-sourced (e.g., Qwen-2-VL-72B) and closed-sourced powerful VLMs (e.g., GPT-4o) with significant margin. This is a great breakthrough since almost all previous VLMs fail or show nearly random performance on representative AVR benchmarks. Our key success is our innovative data synthesis and post-training process, aiming to fully relieve the t","authors_text":"Gang Zhang, Jiangjiang Liu, Ke Zhu, Qunyi Xie, Shanshan Liu, Yu Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T03:18:24Z","title":"On Data Synthesis and Post-training for Visual Abstract Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01324","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:ac44bf31fd05008759e01010346ba724699185b5eb41f7640bf044f406da08b6","target":"record","created_at":"2026-07-05T10:43:12Z","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":"6cb8ce9a5784ea7cec87340921c586478c496ff7e5df436d0be6320b164fe601","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T03:18:24Z","title_canon_sha256":"76dcd2611cfbe7ddaff6aab49f57bde8b846035438a17927a7a7a8be19301cbb"},"schema_version":"1.0","source":{"id":"2504.01324","kind":"arxiv","version":1}},"canonical_sha256":"1f4e95bac0e0492804a0233235237af68e4e36e5bc59201f5ee90d13c6c0d897","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f4e95bac0e0492804a0233235237af68e4e36e5bc59201f5ee90d13c6c0d897","first_computed_at":"2026-07-05T10:43:12.993959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:12.993959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FVsAbRenIKQ27C0wDFeiRX3pK0cCB3ctoZBiFTBBIoRASKNDUCWDaHzgA5svSYZsWVrdzKho49Ka7a9bldwkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:12.994436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac44bf31fd05008759e01010346ba724699185b5eb41f7640bf044f406da08b6","sha256:d8e9bac2ab932709b21411ae19434fbf57952b73513dc8c15fc9a56c99fdf254"],"state_sha256":"f41cf75367b47e1babd7a55eed69a3029f814a9b1ed20c36aa3e7a0cfb549ea1"}