{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WSQS5A6ORJEAII5DI6HVTZASUC","short_pith_number":"pith:WSQS5A6O","schema_version":"1.0","canonical_sha256":"b4a12e83ce8a480423a3478f59e412a091866439dda651ff2acc0c48be84fb06","source":{"kind":"arxiv","id":"2606.21496","version":1},"attestation_state":"computed","paper":{"title":"Decoupling the Declarative from the Procedural in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alexandros Kouris, Andreas Sochopoulos, Chris Xiaoxuan Lu, Nikolaos Tsagkas, Oisin Mac Aodha","submitted_at":"2026-06-19T14:43:58Z","abstract_excerpt":"Deploying generalist robotic agents in the real world requires transferable skills. Specifically, a policy trained to clone a behavior from object-specific demonstrations must generalize beyond that object, otherwise data collection requirements become intractable. Recently, fine-tuning of pre-trained billion-parameter Vision-Language Models (VLMs), initially on large-scale robot datasets and then on fewer scenario-specific demonstrations, has emerged as the predominant paradigm for designing Vision-Language-Action (VLA) models. While these policies achieve state-of-the-art manipulation perfor"},"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":"2606.21496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T14:43:58Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"834c076df3565afe7c9766109be2410efdeb1faa1ea3fb8b57e291ba7530219a","abstract_canon_sha256":"b189a0958164df6ef1a53a4a79bef80b07f17ef92798429d65fc8bd9fbf487c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:12.443709Z","signature_b64":"xyjSB9cDx6TE3LAOGx5AIcuGhgDJKtBeICDiguIJMLACHdTVGlF52sRl5m9Lfv4OO51/BSiqKRIJEfsGKatxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4a12e83ce8a480423a3478f59e412a091866439dda651ff2acc0c48be84fb06","last_reissued_at":"2026-06-23T01:13:12.443134Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:12.443134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling the Declarative from the Procedural in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alexandros Kouris, Andreas Sochopoulos, Chris Xiaoxuan Lu, Nikolaos Tsagkas, Oisin Mac Aodha","submitted_at":"2026-06-19T14:43:58Z","abstract_excerpt":"Deploying generalist robotic agents in the real world requires transferable skills. Specifically, a policy trained to clone a behavior from object-specific demonstrations must generalize beyond that object, otherwise data collection requirements become intractable. Recently, fine-tuning of pre-trained billion-parameter Vision-Language Models (VLMs), initially on large-scale robot datasets and then on fewer scenario-specific demonstrations, has emerged as the predominant paradigm for designing Vision-Language-Action (VLA) models. While these policies achieve state-of-the-art manipulation perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21496","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/2606.21496/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":"2606.21496","created_at":"2026-06-23T01:13:12.443218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21496v1","created_at":"2026-06-23T01:13:12.443218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21496","created_at":"2026-06-23T01:13:12.443218+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSQS5A6ORJEA","created_at":"2026-06-23T01:13:12.443218+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSQS5A6ORJEAII5D","created_at":"2026-06-23T01:13:12.443218+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSQS5A6O","created_at":"2026-06-23T01:13:12.443218+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/WSQS5A6ORJEAII5DI6HVTZASUC","json":"https://pith.science/pith/WSQS5A6ORJEAII5DI6HVTZASUC.json","graph_json":"https://pith.science/api/pith-number/WSQS5A6ORJEAII5DI6HVTZASUC/graph.json","events_json":"https://pith.science/api/pith-number/WSQS5A6ORJEAII5DI6HVTZASUC/events.json","paper":"https://pith.science/paper/WSQS5A6O"},"agent_actions":{"view_html":"https://pith.science/pith/WSQS5A6ORJEAII5DI6HVTZASUC","download_json":"https://pith.science/pith/WSQS5A6ORJEAII5DI6HVTZASUC.json","view_paper":"https://pith.science/paper/WSQS5A6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21496&json=true","fetch_graph":"https://pith.science/api/pith-number/WSQS5A6ORJEAII5DI6HVTZASUC/graph.json","fetch_events":"https://pith.science/api/pith-number/WSQS5A6ORJEAII5DI6HVTZASUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSQS5A6ORJEAII5DI6HVTZASUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSQS5A6ORJEAII5DI6HVTZASUC/action/storage_attestation","attest_author":"https://pith.science/pith/WSQS5A6ORJEAII5DI6HVTZASUC/action/author_attestation","sign_citation":"https://pith.science/pith/WSQS5A6ORJEAII5DI6HVTZASUC/action/citation_signature","submit_replication":"https://pith.science/pith/WSQS5A6ORJEAII5DI6HVTZASUC/action/replication_record"}},"created_at":"2026-06-23T01:13:12.443218+00:00","updated_at":"2026-06-23T01:13:12.443218+00:00"}