{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M4G77KIUXCOPG7G76SN2ZR6RK7","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":"d823fc697dd0e101e06a653556323f8bbeabf30deaefd7520e2628637cf46dac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T12:51:25Z","title_canon_sha256":"bc9f47095769bc94d89294267c5fe442ca2d29450a4552695a5493a412eb6a7d"},"schema_version":"1.0","source":{"id":"2606.12028","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12028","created_at":"2026-06-11T01:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12028v1","created_at":"2026-06-11T01:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12028","created_at":"2026-06-11T01:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"M4G77KIUXCOP","created_at":"2026-06-11T01:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"M4G77KIUXCOPG7G7","created_at":"2026-06-11T01:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"M4G77KIU","created_at":"2026-06-11T01:10:43Z"}],"graph_snapshots":[{"event_id":"sha256:21466876804a189293acd30ce9dc91383f5a442fb8eb54d6d9eb0c95b188bfbf","target":"graph","created_at":"2026-06-11T01:10:43Z","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/2606.12028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalizable robot manipulation requires not only task-level reasoning over unseen scenes, but also reliable grounding of visual plans into embodiment-specific execution. To bridge this gap, we propose VICX (Video generation and In-Context eXecution), a decoupled closed-loop manipulation framework. In VICX, a frozen video generation model produces vision-language-conditioned high-level visual plans, while a Video-to-Trajectory In-Context Operator Network (V2T-ICON) serves as the task-agnostic interface that grounds these plans into executable robot-state trajectories. To improve execution gen","authors_text":"Linyan Xiang, Liu Yang, Song Chen, Ying Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T12:51:25Z","title":"VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12028","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":"sha256:1ba3df011c80f6a48e887ffbea125c4db27a4fd713d0b0b7e96de30d49ff8148","target":"record","created_at":"2026-06-11T01:10:43Z","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":"d823fc697dd0e101e06a653556323f8bbeabf30deaefd7520e2628637cf46dac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T12:51:25Z","title_canon_sha256":"bc9f47095769bc94d89294267c5fe442ca2d29450a4552695a5493a412eb6a7d"},"schema_version":"1.0","source":{"id":"2606.12028","kind":"arxiv","version":1}},"canonical_sha256":"670dffa914b89cf37cdff49bacc7d157fc9011358b0e188c072c5836f085c8c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"670dffa914b89cf37cdff49bacc7d157fc9011358b0e188c072c5836f085c8c5","first_computed_at":"2026-06-11T01:10:43.943683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:43.943683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"on7cuRnwZtEIhNWGGNRDe6q65KtzSQHj95u6Af0EkQlljwzv5ZKroadjoZmj7a3wdKBLgiUlQe+7q8QscV6KBA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:43.944484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12028","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ba3df011c80f6a48e887ffbea125c4db27a4fd713d0b0b7e96de30d49ff8148","sha256:21466876804a189293acd30ce9dc91383f5a442fb8eb54d6d9eb0c95b188bfbf"],"state_sha256":"5d35294ddbb6b501b3e0cb6dac337ccf471e42b4d40681594424cf5c2ef5723f"}