{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3RZ5WWPOU55TJAAJ4GKTNU4IIG","short_pith_number":"pith:3RZ5WWPO","schema_version":"1.0","canonical_sha256":"dc73db59eea77b348009e19536d38841b058d8e5c17dc7f629ac71b3f66957b4","source":{"kind":"arxiv","id":"2502.04558","version":1},"attestation_state":"computed","paper":{"title":"Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hengxu Li, Hong Lu, Matthias Scheutz, Prithviraj Singh Shahani, Stephanie Herbers","submitted_at":"2025-02-06T23:11:11Z","abstract_excerpt":"Vision-language-action (VLA) models hold promise as generalist robotics solutions by translating visual and linguistic inputs into robot actions, yet they lack reliability due to their black-box nature and sensitivity to environmental changes. In contrast, cognitive architectures (CA) excel in symbolic reasoning and state monitoring but are constrained by rigid predefined execution. This work bridges these approaches by probing OpenVLA's hidden layers to uncover symbolic representations of object properties, relations, and action states, enabling integration with a CA for enhanced interpretabi"},"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":"2502.04558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-06T23:11:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1cba8db77c0b1e112c9af48477a725726ccb15358501ba0c0e2a36e975fdf85d","abstract_canon_sha256":"37997a7c34eab9a703c2962d955c7d29ee08adc5e91896205f03e34657b9ef10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:53.342720Z","signature_b64":"/8IMCaMDpI9H7WdoJkz2l11sI4u9ZsFjLpNI941qZPn3qiuq+Cq16Dqc4pEitsIr4dTGfyqlH1Ha1LnGPTOYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc73db59eea77b348009e19536d38841b058d8e5c17dc7f629ac71b3f66957b4","last_reissued_at":"2026-07-05T10:10:53.342300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:53.342300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hengxu Li, Hong Lu, Matthias Scheutz, Prithviraj Singh Shahani, Stephanie Herbers","submitted_at":"2025-02-06T23:11:11Z","abstract_excerpt":"Vision-language-action (VLA) models hold promise as generalist robotics solutions by translating visual and linguistic inputs into robot actions, yet they lack reliability due to their black-box nature and sensitivity to environmental changes. In contrast, cognitive architectures (CA) excel in symbolic reasoning and state monitoring but are constrained by rigid predefined execution. This work bridges these approaches by probing OpenVLA's hidden layers to uncover symbolic representations of object properties, relations, and action states, enabling integration with a CA for enhanced interpretabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04558","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/2502.04558/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":"2502.04558","created_at":"2026-07-05T10:10:53.342368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04558v1","created_at":"2026-07-05T10:10:53.342368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04558","created_at":"2026-07-05T10:10:53.342368+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RZ5WWPOU55T","created_at":"2026-07-05T10:10:53.342368+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RZ5WWPOU55TJAAJ","created_at":"2026-07-05T10:10:53.342368+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RZ5WWPO","created_at":"2026-07-05T10:10:53.342368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10495","citing_title":"Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG","json":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG.json","graph_json":"https://pith.science/api/pith-number/3RZ5WWPOU55TJAAJ4GKTNU4IIG/graph.json","events_json":"https://pith.science/api/pith-number/3RZ5WWPOU55TJAAJ4GKTNU4IIG/events.json","paper":"https://pith.science/paper/3RZ5WWPO"},"agent_actions":{"view_html":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG","download_json":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG.json","view_paper":"https://pith.science/paper/3RZ5WWPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04558&json=true","fetch_graph":"https://pith.science/api/pith-number/3RZ5WWPOU55TJAAJ4GKTNU4IIG/graph.json","fetch_events":"https://pith.science/api/pith-number/3RZ5WWPOU55TJAAJ4GKTNU4IIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG/action/storage_attestation","attest_author":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG/action/author_attestation","sign_citation":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG/action/citation_signature","submit_replication":"https://pith.science/pith/3RZ5WWPOU55TJAAJ4GKTNU4IIG/action/replication_record"}},"created_at":"2026-07-05T10:10:53.342368+00:00","updated_at":"2026-07-05T10:10:53.342368+00:00"}