{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QI642LN6OKZKB6JESI7R6ZAGRY","short_pith_number":"pith:QI642LN6","schema_version":"1.0","canonical_sha256":"823dcd2dbe72b2a0f924923f1f64068e00d09eaa47a564beef1a4ae8fb6c2388","source":{"kind":"arxiv","id":"2512.10342","version":3},"attestation_state":"computed","paper":{"title":"CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akash Kumar, Priyank Pathak, Shresth Grover, Yogesh S Rawat","submitted_at":"2025-12-11T06:46:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2512.10342","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T06:46:51Z","cross_cats_sorted":[],"title_canon_sha256":"1f5992cc4bf6ad1257bb7de3a2775c3bf6ba5f1c5b9337550ab13c8a2e66381e","abstract_canon_sha256":"1f7c697a439dcbebb6f06cb59900bf67f88863ce4b044d7c0177cf28058d84e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:08.687872Z","signature_b64":"p3nL/0gfQ8OsHOZ6WO5+x8XNA6zGTOep05QTZ8a5SCQPbLiwpchh63y4uKYgqGKd0UNVk7aA9dsQj8C5uBtBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"823dcd2dbe72b2a0f924923f1f64068e00d09eaa47a564beef1a4ae8fb6c2388","last_reissued_at":"2026-06-30T00:15:08.687366Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:08.687366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akash Kumar, Priyank Pathak, Shresth Grover, Yogesh S Rawat","submitted_at":"2025-12-11T06:46:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10342","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.10342/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2512.10342","created_at":"2026-06-30T00:15:08.687434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.10342v3","created_at":"2026-06-30T00:15:08.687434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10342","created_at":"2026-06-30T00:15:08.687434+00:00"},{"alias_kind":"pith_short_12","alias_value":"QI642LN6OKZK","created_at":"2026-06-30T00:15:08.687434+00:00"},{"alias_kind":"pith_short_16","alias_value":"QI642LN6OKZKB6JE","created_at":"2026-06-30T00:15:08.687434+00:00"},{"alias_kind":"pith_short_8","alias_value":"QI642LN6","created_at":"2026-06-30T00:15:08.687434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY","json":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY.json","graph_json":"https://pith.science/api/pith-number/QI642LN6OKZKB6JESI7R6ZAGRY/graph.json","events_json":"https://pith.science/api/pith-number/QI642LN6OKZKB6JESI7R6ZAGRY/events.json","paper":"https://pith.science/paper/QI642LN6"},"agent_actions":{"view_html":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY","download_json":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY.json","view_paper":"https://pith.science/paper/QI642LN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.10342&json=true","fetch_graph":"https://pith.science/api/pith-number/QI642LN6OKZKB6JESI7R6ZAGRY/graph.json","fetch_events":"https://pith.science/api/pith-number/QI642LN6OKZKB6JESI7R6ZAGRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY/action/storage_attestation","attest_author":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY/action/author_attestation","sign_citation":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY/action/citation_signature","submit_replication":"https://pith.science/pith/QI642LN6OKZKB6JESI7R6ZAGRY/action/replication_record"}},"created_at":"2026-06-30T00:15:08.687434+00:00","updated_at":"2026-06-30T00:15:08.687434+00:00"}