{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WECNXRCSCN5SQK5VME7R6POSDY","short_pith_number":"pith:WECNXRCS","schema_version":"1.0","canonical_sha256":"b104dbc452137b282bb5613f1f3dd21e093da3cf9092959b2bbf0f0b770f9638","source":{"kind":"arxiv","id":"2605.17517","version":1},"attestation_state":"computed","paper":{"title":"AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huixu Dong, Weijie Kong, Wei Yu, Zhian Su","submitted_at":"2026-05-17T16:02:05Z","abstract_excerpt":"Recent advances in Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation. However, the visual representations of most VLA models are often dominated by global object appearance and struggle to focus on task-relevant functional interaction regions, which limits their robustness in unstructured environments. Existing affordance-based methods typically rely on explicit mask injection or external perception modules, requiring additional annotations while introducing cascading perception errors and inference overhead. To address these limitations, "},"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":"2605.17517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-17T16:02:05Z","cross_cats_sorted":[],"title_canon_sha256":"29614ee6dcac1a699768d5704cc622e957fff719035fe15dd920527dd03aaa18","abstract_canon_sha256":"465b970b2ac2c83fe94247ecd64e5eb5608bef6b457a2d76a281ca8c5f8aacf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:43.313600Z","signature_b64":"hcIEp5ZBsvwbpSfm+FRdn5innGdhaRZMeQ7VAfzA/xlMWoSxhCKbLWtEt9bGcw1lNBUzQg0S4NYRwS+wvj4nDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b104dbc452137b282bb5613f1f3dd21e093da3cf9092959b2bbf0f0b770f9638","last_reissued_at":"2026-05-20T00:04:43.312782Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:43.312782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huixu Dong, Weijie Kong, Wei Yu, Zhian Su","submitted_at":"2026-05-17T16:02:05Z","abstract_excerpt":"Recent advances in Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation. However, the visual representations of most VLA models are often dominated by global object appearance and struggle to focus on task-relevant functional interaction regions, which limits their robustness in unstructured environments. Existing affordance-based methods typically rely on explicit mask injection or external perception modules, requiring additional annotations while introducing cascading perception errors and inference overhead. To address these limitations, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17517","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/2605.17517/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.648679Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.626914Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"1c68d08ddf9e64b2b007b17fae376d7c265253c47791ab74cc19fec7ff1e2d4f"},"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":"2605.17517","created_at":"2026-05-20T00:04:43.312909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17517v1","created_at":"2026-05-20T00:04:43.312909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17517","created_at":"2026-05-20T00:04:43.312909+00:00"},{"alias_kind":"pith_short_12","alias_value":"WECNXRCSCN5S","created_at":"2026-05-20T00:04:43.312909+00:00"},{"alias_kind":"pith_short_16","alias_value":"WECNXRCSCN5SQK5V","created_at":"2026-05-20T00:04:43.312909+00:00"},{"alias_kind":"pith_short_8","alias_value":"WECNXRCS","created_at":"2026-05-20T00:04:43.312909+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/WECNXRCSCN5SQK5VME7R6POSDY","json":"https://pith.science/pith/WECNXRCSCN5SQK5VME7R6POSDY.json","graph_json":"https://pith.science/api/pith-number/WECNXRCSCN5SQK5VME7R6POSDY/graph.json","events_json":"https://pith.science/api/pith-number/WECNXRCSCN5SQK5VME7R6POSDY/events.json","paper":"https://pith.science/paper/WECNXRCS"},"agent_actions":{"view_html":"https://pith.science/pith/WECNXRCSCN5SQK5VME7R6POSDY","download_json":"https://pith.science/pith/WECNXRCSCN5SQK5VME7R6POSDY.json","view_paper":"https://pith.science/paper/WECNXRCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17517&json=true","fetch_graph":"https://pith.science/api/pith-number/WECNXRCSCN5SQK5VME7R6POSDY/graph.json","fetch_events":"https://pith.science/api/pith-number/WECNXRCSCN5SQK5VME7R6POSDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WECNXRCSCN5SQK5VME7R6POSDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WECNXRCSCN5SQK5VME7R6POSDY/action/storage_attestation","attest_author":"https://pith.science/pith/WECNXRCSCN5SQK5VME7R6POSDY/action/author_attestation","sign_citation":"https://pith.science/pith/WECNXRCSCN5SQK5VME7R6POSDY/action/citation_signature","submit_replication":"https://pith.science/pith/WECNXRCSCN5SQK5VME7R6POSDY/action/replication_record"}},"created_at":"2026-05-20T00:04:43.312909+00:00","updated_at":"2026-05-20T00:04:43.312909+00:00"}