{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VC5POVGSLKGNHZLCACEOONPR3H","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":"5249b2ec8c5fd22ccaa10ec691f39ed638ae87346c2e7aafa10d4929f76abbb6","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T13:28:51Z","title_canon_sha256":"ef4104c53aced6072ec907a7274d0e5b433bb28da5784307f4134698c7903b95"},"schema_version":"1.0","source":{"id":"2606.06155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06155","created_at":"2026-06-05T01:15:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06155v1","created_at":"2026-06-05T01:15:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06155","created_at":"2026-06-05T01:15:35Z"},{"alias_kind":"pith_short_12","alias_value":"VC5POVGSLKGN","created_at":"2026-06-05T01:15:35Z"},{"alias_kind":"pith_short_16","alias_value":"VC5POVGSLKGNHZLC","created_at":"2026-06-05T01:15:35Z"},{"alias_kind":"pith_short_8","alias_value":"VC5POVGS","created_at":"2026-06-05T01:15:35Z"}],"graph_snapshots":[{"event_id":"sha256:922c839c568e565d797f11170519193691cfd4c1b4294ed2a39a07cd04e0fb2e","target":"graph","created_at":"2026-06-05T01:15:35Z","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/2606.06155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models leverage the rich world knowledge of pretrained vision-language models (VLMs) to enable instruction-following robotic manipulation. However, the structural mismatch between VLM semantic spaces and embodied control policies often hinders the learning of precise perception--action mappings. To address this challenge, we propose \\textbf{AffordanceVLA}, a unified framework that introduces structured affordance forecasting as a task-oriented intermediate representation to establish a more precise and robust perception--action mapping. Specifically, we progressive","authors_text":"Bowen Ping, Jiadi You, Jiaqi Liang, Junwei Liang, Minghong Cai, Qize Yu, Ruihai Wu, Yang Tian, Yinchuan Li, Yingcong Chen, Yue Chen, Yuran Wang, Zeying Gong","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T13:28:51Z","title":"AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06155","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":"sha256:1784c5a50b20e18de4c4547cbea308d9d3db4e6bae0d02f32f30851a5c17f32a","target":"record","created_at":"2026-06-05T01:15:35Z","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":"5249b2ec8c5fd22ccaa10ec691f39ed638ae87346c2e7aafa10d4929f76abbb6","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T13:28:51Z","title_canon_sha256":"ef4104c53aced6072ec907a7274d0e5b433bb28da5784307f4134698c7903b95"},"schema_version":"1.0","source":{"id":"2606.06155","kind":"arxiv","version":1}},"canonical_sha256":"a8baf754d25a8cd3e5620088e735f1d9ecf39479e4bbf5da4a48f79d08e28f92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8baf754d25a8cd3e5620088e735f1d9ecf39479e4bbf5da4a48f79d08e28f92","first_computed_at":"2026-06-05T01:15:35.616192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:35.616192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"auSt4S6vGPUiFo/WRqtw0t0pQZbut8XWvljVK2+q1pNB6WggeFqJJ7vnj87hvVEbf0/hOZUO09UN3ApcaiD1Cg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:35.616614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1784c5a50b20e18de4c4547cbea308d9d3db4e6bae0d02f32f30851a5c17f32a","sha256:922c839c568e565d797f11170519193691cfd4c1b4294ed2a39a07cd04e0fb2e"],"state_sha256":"2161f9a51b89e63124c0ab6ecef0f8ba7306578be3cc881a2e0967a82e303896"}