{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZQHGHPB6NJY3BYLM2WY37BYCQC","short_pith_number":"pith:ZQHGHPB6","schema_version":"1.0","canonical_sha256":"cc0e63bc3e6a71b0e16cd5b1bf870280908287756d34383ba463405a8b85efb3","source":{"kind":"arxiv","id":"2403.10700","version":2},"attestation_state":"computed","paper":{"title":"Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Alberto Castellini, Alessandro Farinelli, Alessio Del Bue, Francesco Taioli, Lorenzo Natale, Marco Cristani, Stefano Rosa, Yiming Wang","submitted_at":"2024-03-15T21:36:15Z","abstract_excerpt":"Vision-and-Language Navigation in Continuous Environments (VLN-CE) is one of the most intuitive yet challenging embodied AI tasks. Agents are tasked to navigate towards a target goal by executing a set of low-level actions, following a series of natural language instructions. All VLN-CE methods in the literature assume that language instructions are exact. However, in practice, instructions given by humans can contain errors when describing a spatial environment due to inaccurate memory or confusion. Current VLN-CE benchmarks do not address this scenario, making the state-of-the-art methods in"},"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":"2403.10700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-15T21:36:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"34d0496f6744d1e66fb9b41691ddf0d671de93febcc1a1ae4d926eb77b095184","abstract_canon_sha256":"be817e2e968eb24a18590d3518ab3c7abf65bb36a7f1c5e576a85ec20ad6678a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:12.169404Z","signature_b64":"1HOIkgqDAEOjk3fU77Md8vDGFKNrJzOkPrLQpiq0wUenV9OnGyKCDgarEoa2SkLza8OjUNtP1onQFMVbUg0oBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc0e63bc3e6a71b0e16cd5b1bf870280908287756d34383ba463405a8b85efb3","last_reissued_at":"2026-07-05T10:01:12.168864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:12.168864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Alberto Castellini, Alessandro Farinelli, Alessio Del Bue, Francesco Taioli, Lorenzo Natale, Marco Cristani, Stefano Rosa, Yiming Wang","submitted_at":"2024-03-15T21:36:15Z","abstract_excerpt":"Vision-and-Language Navigation in Continuous Environments (VLN-CE) is one of the most intuitive yet challenging embodied AI tasks. Agents are tasked to navigate towards a target goal by executing a set of low-level actions, following a series of natural language instructions. All VLN-CE methods in the literature assume that language instructions are exact. However, in practice, instructions given by humans can contain errors when describing a spatial environment due to inaccurate memory or confusion. Current VLN-CE benchmarks do not address this scenario, making the state-of-the-art methods in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10700","kind":"arxiv","version":2},"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/2403.10700/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":"2403.10700","created_at":"2026-07-05T10:01:12.168919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10700v2","created_at":"2026-07-05T10:01:12.168919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10700","created_at":"2026-07-05T10:01:12.168919+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQHGHPB6NJY3","created_at":"2026-07-05T10:01:12.168919+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQHGHPB6NJY3BYLM","created_at":"2026-07-05T10:01:12.168919+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQHGHPB6","created_at":"2026-07-05T10:01:12.168919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10726","citing_title":"NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC","json":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC.json","graph_json":"https://pith.science/api/pith-number/ZQHGHPB6NJY3BYLM2WY37BYCQC/graph.json","events_json":"https://pith.science/api/pith-number/ZQHGHPB6NJY3BYLM2WY37BYCQC/events.json","paper":"https://pith.science/paper/ZQHGHPB6"},"agent_actions":{"view_html":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC","download_json":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC.json","view_paper":"https://pith.science/paper/ZQHGHPB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10700&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQHGHPB6NJY3BYLM2WY37BYCQC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQHGHPB6NJY3BYLM2WY37BYCQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC/action/storage_attestation","attest_author":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC/action/author_attestation","sign_citation":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC/action/citation_signature","submit_replication":"https://pith.science/pith/ZQHGHPB6NJY3BYLM2WY37BYCQC/action/replication_record"}},"created_at":"2026-07-05T10:01:12.168919+00:00","updated_at":"2026-07-05T10:01:12.168919+00:00"}