{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IOYXYVJQ476G3BHU7ZHRE3GNQ2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5b6fe40f8b7e50734a49e29d6058c5cb54159ad2b58898045873d9c78b57583d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T05:17:02Z","title_canon_sha256":"9e4a9c200387e830e751cd5374455cd5bf532bbf004380d7a17a604329f001ed"},"schema_version":"1.0","source":{"id":"2606.31144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31144","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31144v1","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31144","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"IOYXYVJQ476G","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"IOYXYVJQ476G3BHU","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"IOYXYVJQ","created_at":"2026-07-01T01:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:a816b1dfefc4d3f83b755f40f3a4cc3bd7f45877441b970b3b549e4d57b03bd8","target":"graph","created_at":"2026-07-01T01:17:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.31144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents an integrated system for the CMU Vision-Language-Action (VLA) Challenge, designed to enable an autonomous agent to perform complex tasks based on natural language instructions. Our framework employs a modular architecture that orchestrates environment mapping, question processing, and navigation. The system operates in two parallel streams: a perception pipeline that constructs a semantic voxel map from real-time camera feeds using OwlViT embeddings, and a language pipeline that classifies user commands with a Vision-Language Model. The mapping is time-constrained; the syst","authors_text":"Anindya Jana, Arup Sadhu, Ranjan Dasgupta, Snehasis Banerjee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T05:17:02Z","title":"A Modular Vision-Language-Action Robotics Framework for Indoor Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31144","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:03cc3ee65eee9be265fca28f2d20be00bf9083a3b061b59bcaaec18879de9859","target":"record","created_at":"2026-07-01T01:17:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5b6fe40f8b7e50734a49e29d6058c5cb54159ad2b58898045873d9c78b57583d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T05:17:02Z","title_canon_sha256":"9e4a9c200387e830e751cd5374455cd5bf532bbf004380d7a17a604329f001ed"},"schema_version":"1.0","source":{"id":"2606.31144","kind":"arxiv","version":1}},"canonical_sha256":"43b17c5530e7fc6d84f4fe4f126ccd86b3d5bab5d5890e6a9c2f4eb332c60dd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43b17c5530e7fc6d84f4fe4f126ccd86b3d5bab5d5890e6a9c2f4eb332c60dd1","first_computed_at":"2026-07-01T01:17:30.443028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:30.443028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N5I19zWPdlOt/TqihHuBpV1h6E5blObyo2WwdybI6cSrNJChvtJNg4h4R4Ts016mG7qazyeY4RnEc8gY4gkECQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:30.443567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03cc3ee65eee9be265fca28f2d20be00bf9083a3b061b59bcaaec18879de9859","sha256:a816b1dfefc4d3f83b755f40f3a4cc3bd7f45877441b970b3b549e4d57b03bd8"],"state_sha256":"bcdfecc5ff7d9b088deb358b9302239d1420d77cbdf1d9ff6470a7c929779252"}