{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QI642LN6OKZKB6JESI7R6ZAGRY","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":"1f7c697a439dcbebb6f06cb59900bf67f88863ce4b044d7c0177cf28058d84e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T06:46:51Z","title_canon_sha256":"1f5992cc4bf6ad1257bb7de3a2775c3bf6ba5f1c5b9337550ab13c8a2e66381e"},"schema_version":"1.0","source":{"id":"2512.10342","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10342","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10342v3","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10342","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"QI642LN6OKZK","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"QI642LN6OKZKB6JE","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"QI642LN6","created_at":"2026-06-30T00:15:08Z"}],"graph_snapshots":[{"event_id":"sha256:970046e7209b93caf64a5f6cf2faf61e6e48457ee9264e0af5e3de6871dde8fe","target":"graph","created_at":"2026-06-30T00:15:08Z","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/2512.10342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) have shown promising planning capabilities, yet their success remains confined to the text domain, leaving visual decision-making relatively underexplored. Addressing this gap, we introduce Corrective Sequence Planning (CoSPlan) benchmark, where VLMs must plan a sequence of visual actions from an initial scene to a target scene. CoSPlan evaluates models on their ability to imagine and execute a coherent set of visual steps required to reach the goal (Step Completion). To prevent any shortcuts that simply describe the final scene, we introduce an erroneous action i","authors_text":"Akash Kumar, Priyank Pathak, Shresth Grover, Yogesh S Rawat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T06:46:51Z","title":"CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10342","kind":"arxiv","version":3},"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":"sha256:764089d75cd78cbdf44d0d991918a7151c0620c7454a5f2f9b07b5c88a9676ae","target":"record","created_at":"2026-06-30T00:15:08Z","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":"1f7c697a439dcbebb6f06cb59900bf67f88863ce4b044d7c0177cf28058d84e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T06:46:51Z","title_canon_sha256":"1f5992cc4bf6ad1257bb7de3a2775c3bf6ba5f1c5b9337550ab13c8a2e66381e"},"schema_version":"1.0","source":{"id":"2512.10342","kind":"arxiv","version":3}},"canonical_sha256":"823dcd2dbe72b2a0f924923f1f64068e00d09eaa47a564beef1a4ae8fb6c2388","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"823dcd2dbe72b2a0f924923f1f64068e00d09eaa47a564beef1a4ae8fb6c2388","first_computed_at":"2026-06-30T00:15:08.687366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:08.687366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p3nL/0gfQ8OsHOZ6WO5+x8XNA6zGTOep05QTZ8a5SCQPbLiwpchh63y4uKYgqGKd0UNVk7aA9dsQj8C5uBtBAw==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:08.687872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.10342","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:764089d75cd78cbdf44d0d991918a7151c0620c7454a5f2f9b07b5c88a9676ae","sha256:970046e7209b93caf64a5f6cf2faf61e6e48457ee9264e0af5e3de6871dde8fe"],"state_sha256":"5b045f357d91205c7ed41ca917dbfec582ddbede67e48e5ccaf7a96d336bf4f7"}