{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VC5POVGSLKGNHZLCACEOONPR3H","short_pith_number":"pith:VC5POVGS","schema_version":"1.0","canonical_sha256":"a8baf754d25a8cd3e5620088e735f1d9ecf39479e4bbf5da4a48f79d08e28f92","source":{"kind":"arxiv","id":"2606.06155","version":1},"attestation_state":"computed","paper":{"title":"AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.RO","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","submitted_at":"2026-06-04T13:28:51Z","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"},"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":"2606.06155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T13:28:51Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"ef4104c53aced6072ec907a7274d0e5b433bb28da5784307f4134698c7903b95","abstract_canon_sha256":"5249b2ec8c5fd22ccaa10ec691f39ed638ae87346c2e7aafa10d4929f76abbb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:35.616614Z","signature_b64":"auSt4S6vGPUiFo/WRqtw0t0pQZbut8XWvljVK2+q1pNB6WggeFqJJ7vnj87hvVEbf0/hOZUO09UN3ApcaiD1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8baf754d25a8cd3e5620088e735f1d9ecf39479e4bbf5da4a48f79d08e28f92","last_reissued_at":"2026-06-05T01:15:35.616192Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:35.616192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.RO","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","submitted_at":"2026-06-04T13:28:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06155","kind":"arxiv","version":1},"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/2606.06155/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":"2606.06155","created_at":"2026-06-05T01:15:35.616251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06155v1","created_at":"2026-06-05T01:15:35.616251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06155","created_at":"2026-06-05T01:15:35.616251+00:00"},{"alias_kind":"pith_short_12","alias_value":"VC5POVGSLKGN","created_at":"2026-06-05T01:15:35.616251+00:00"},{"alias_kind":"pith_short_16","alias_value":"VC5POVGSLKGNHZLC","created_at":"2026-06-05T01:15:35.616251+00:00"},{"alias_kind":"pith_short_8","alias_value":"VC5POVGS","created_at":"2026-06-05T01:15:35.616251+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/VC5POVGSLKGNHZLCACEOONPR3H","json":"https://pith.science/pith/VC5POVGSLKGNHZLCACEOONPR3H.json","graph_json":"https://pith.science/api/pith-number/VC5POVGSLKGNHZLCACEOONPR3H/graph.json","events_json":"https://pith.science/api/pith-number/VC5POVGSLKGNHZLCACEOONPR3H/events.json","paper":"https://pith.science/paper/VC5POVGS"},"agent_actions":{"view_html":"https://pith.science/pith/VC5POVGSLKGNHZLCACEOONPR3H","download_json":"https://pith.science/pith/VC5POVGSLKGNHZLCACEOONPR3H.json","view_paper":"https://pith.science/paper/VC5POVGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06155&json=true","fetch_graph":"https://pith.science/api/pith-number/VC5POVGSLKGNHZLCACEOONPR3H/graph.json","fetch_events":"https://pith.science/api/pith-number/VC5POVGSLKGNHZLCACEOONPR3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VC5POVGSLKGNHZLCACEOONPR3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VC5POVGSLKGNHZLCACEOONPR3H/action/storage_attestation","attest_author":"https://pith.science/pith/VC5POVGSLKGNHZLCACEOONPR3H/action/author_attestation","sign_citation":"https://pith.science/pith/VC5POVGSLKGNHZLCACEOONPR3H/action/citation_signature","submit_replication":"https://pith.science/pith/VC5POVGSLKGNHZLCACEOONPR3H/action/replication_record"}},"created_at":"2026-06-05T01:15:35.616251+00:00","updated_at":"2026-06-05T01:15:35.616251+00:00"}