{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XJAESYJDNCYFBD7KYNFRE6QGYR","short_pith_number":"pith:XJAESYJD","schema_version":"1.0","canonical_sha256":"ba4049612368b0508feac34b127a06c4697ff97531b08a0e8861bfe45c4803c0","source":{"kind":"arxiv","id":"2606.19297","version":1},"attestation_state":"computed","paper":{"title":"Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Albina Burlova, Aleksandr I. Panov, Alexey K. Kovalev, Andrey Kuznetsov, Andrey Moskalenko, Daria Pugacheva, Denis Shepelev, Elena Tutubalina, Matvey Skripkin, Mikhail Kolosov, Nikita Kachaev, Nikita Kurlaev, Vlad Shakhuro","submitted_at":"2026-06-17T17:20:46Z","abstract_excerpt":"Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to answer through action. Each question becomes a short tabletop episode where the agent performs a single object-placement action "},"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":"2606.19297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T17:20:46Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"cbcddd741d5fa25bb67892057518a968ef6d0fad7785f7ee4af7130c775e9134","abstract_canon_sha256":"a5798cdf089049973c6270a12d6d2a9a776e0f16a554e81bb555dd47f78f761e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:10.048294Z","signature_b64":"s2FifD+x7Ry9cmnoQtp1kP86v6/Fs8RlQNvGOeplYZxo2KlWqT4aoAcm7g/9PFM55FNQyZkkUOCRFgqQnqeuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba4049612368b0508feac34b127a06c4697ff97531b08a0e8861bfe45c4803c0","last_reissued_at":"2026-06-19T16:12:10.047954Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:10.047954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Albina Burlova, Aleksandr I. Panov, Alexey K. Kovalev, Andrey Kuznetsov, Andrey Moskalenko, Daria Pugacheva, Denis Shepelev, Elena Tutubalina, Matvey Skripkin, Mikhail Kolosov, Nikita Kachaev, Nikita Kurlaev, Vlad Shakhuro","submitted_at":"2026-06-17T17:20:46Z","abstract_excerpt":"Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to answer through action. Each question becomes a short tabletop episode where the agent performs a single object-placement action "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19297","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/2606.19297/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":"2606.19297","created_at":"2026-06-19T16:12:10.048014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19297v1","created_at":"2026-06-19T16:12:10.048014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19297","created_at":"2026-06-19T16:12:10.048014+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJAESYJDNCYF","created_at":"2026-06-19T16:12:10.048014+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJAESYJDNCYFBD7K","created_at":"2026-06-19T16:12:10.048014+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJAESYJD","created_at":"2026-06-19T16:12:10.048014+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/XJAESYJDNCYFBD7KYNFRE6QGYR","json":"https://pith.science/pith/XJAESYJDNCYFBD7KYNFRE6QGYR.json","graph_json":"https://pith.science/api/pith-number/XJAESYJDNCYFBD7KYNFRE6QGYR/graph.json","events_json":"https://pith.science/api/pith-number/XJAESYJDNCYFBD7KYNFRE6QGYR/events.json","paper":"https://pith.science/paper/XJAESYJD"},"agent_actions":{"view_html":"https://pith.science/pith/XJAESYJDNCYFBD7KYNFRE6QGYR","download_json":"https://pith.science/pith/XJAESYJDNCYFBD7KYNFRE6QGYR.json","view_paper":"https://pith.science/paper/XJAESYJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19297&json=true","fetch_graph":"https://pith.science/api/pith-number/XJAESYJDNCYFBD7KYNFRE6QGYR/graph.json","fetch_events":"https://pith.science/api/pith-number/XJAESYJDNCYFBD7KYNFRE6QGYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJAESYJDNCYFBD7KYNFRE6QGYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJAESYJDNCYFBD7KYNFRE6QGYR/action/storage_attestation","attest_author":"https://pith.science/pith/XJAESYJDNCYFBD7KYNFRE6QGYR/action/author_attestation","sign_citation":"https://pith.science/pith/XJAESYJDNCYFBD7KYNFRE6QGYR/action/citation_signature","submit_replication":"https://pith.science/pith/XJAESYJDNCYFBD7KYNFRE6QGYR/action/replication_record"}},"created_at":"2026-06-19T16:12:10.048014+00:00","updated_at":"2026-06-19T16:12:10.048014+00:00"}