{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7UQGVJFL5V42DMWEZIDKX7A3D7","short_pith_number":"pith:7UQGVJFL","schema_version":"1.0","canonical_sha256":"fd206aa4abed79a1b2c4ca06abfc1b1fec36fb0e5f891786ac490ed7f1c01d4d","source":{"kind":"arxiv","id":"2606.23157","version":1},"attestation_state":"computed","paper":{"title":"Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alaa Elkamash, Ali Alabbas, Camillo Murgia, Dipshikha Das, Philip Long, Sainul Ansary","submitted_at":"2026-06-22T11:01:56Z","abstract_excerpt":"This paper presents a modular training-free framework for zero-shot, language-guided robotic manipulation in semi-structured environments. The architecture bridges the gap between high-level reasoning and low-level kinematics by decomposing the vision-action pipeline into three stages: visual perception, semantic interpretation, and task execution. To overcome the spatial ambiguity and semantic hallucinations inherent in standard Vision-Language Models (VLMs), the perception module employs FastSAM and Set-of-Mark (SoM) prompting to dynamically generate grounded, alphanumeric visual anchors. Th"},"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":"2606.23157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T11:01:56Z","cross_cats_sorted":[],"title_canon_sha256":"6877081fa6283614c958c01444b5e56cd308ce48a5f0caef3678658b0f4842db","abstract_canon_sha256":"94d2e32da5b1b7fa6fd3c5dcd1d165277d95e5f92a299eba8fddaedb7ebc31c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:11.625745Z","signature_b64":"RTMeC1RrhQOb4gi4f11W7TJ1OUk/IE8C+rmcUbTbAP/Td7TNpkAAWTdLwiUhlvdAZcPAelFJggTnN/kc5KgtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd206aa4abed79a1b2c4ca06abfc1b1fec36fb0e5f891786ac490ed7f1c01d4d","last_reissued_at":"2026-06-23T03:14:11.625347Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:11.625347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alaa Elkamash, Ali Alabbas, Camillo Murgia, Dipshikha Das, Philip Long, Sainul Ansary","submitted_at":"2026-06-22T11:01:56Z","abstract_excerpt":"This paper presents a modular training-free framework for zero-shot, language-guided robotic manipulation in semi-structured environments. The architecture bridges the gap between high-level reasoning and low-level kinematics by decomposing the vision-action pipeline into three stages: visual perception, semantic interpretation, and task execution. To overcome the spatial ambiguity and semantic hallucinations inherent in standard Vision-Language Models (VLMs), the perception module employs FastSAM and Set-of-Mark (SoM) prompting to dynamically generate grounded, alphanumeric visual anchors. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23157","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/2606.23157/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":"2606.23157","created_at":"2026-06-23T03:14:11.625403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23157v1","created_at":"2026-06-23T03:14:11.625403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23157","created_at":"2026-06-23T03:14:11.625403+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UQGVJFL5V42","created_at":"2026-06-23T03:14:11.625403+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UQGVJFL5V42DMWE","created_at":"2026-06-23T03:14:11.625403+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UQGVJFL","created_at":"2026-06-23T03:14:11.625403+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/7UQGVJFL5V42DMWEZIDKX7A3D7","json":"https://pith.science/pith/7UQGVJFL5V42DMWEZIDKX7A3D7.json","graph_json":"https://pith.science/api/pith-number/7UQGVJFL5V42DMWEZIDKX7A3D7/graph.json","events_json":"https://pith.science/api/pith-number/7UQGVJFL5V42DMWEZIDKX7A3D7/events.json","paper":"https://pith.science/paper/7UQGVJFL"},"agent_actions":{"view_html":"https://pith.science/pith/7UQGVJFL5V42DMWEZIDKX7A3D7","download_json":"https://pith.science/pith/7UQGVJFL5V42DMWEZIDKX7A3D7.json","view_paper":"https://pith.science/paper/7UQGVJFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23157&json=true","fetch_graph":"https://pith.science/api/pith-number/7UQGVJFL5V42DMWEZIDKX7A3D7/graph.json","fetch_events":"https://pith.science/api/pith-number/7UQGVJFL5V42DMWEZIDKX7A3D7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UQGVJFL5V42DMWEZIDKX7A3D7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UQGVJFL5V42DMWEZIDKX7A3D7/action/storage_attestation","attest_author":"https://pith.science/pith/7UQGVJFL5V42DMWEZIDKX7A3D7/action/author_attestation","sign_citation":"https://pith.science/pith/7UQGVJFL5V42DMWEZIDKX7A3D7/action/citation_signature","submit_replication":"https://pith.science/pith/7UQGVJFL5V42DMWEZIDKX7A3D7/action/replication_record"}},"created_at":"2026-06-23T03:14:11.625403+00:00","updated_at":"2026-06-23T03:14:11.625403+00:00"}