{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:47X77RMF43ET2ZUT64ANNOLMKL","short_pith_number":"pith:47X77RMF","schema_version":"1.0","canonical_sha256":"e7efffc585e6c93d6693f700d6b96c52ec3cde6a113e00bad9890fb353cb4997","source":{"kind":"arxiv","id":"2506.04089","version":1},"attestation_state":"computed","paper":{"title":"AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aleksandr I. Panov, Alexey K. Kovalev, Anastasiia Ivanova, Eva Bakaeva, Zoya Volovikova","submitted_at":"2025-06-04T15:47:07Z","abstract_excerpt":"As a part of an embodied agent, Large Language Models (LLMs) are typically used for behavior planning given natural language instructions from the user. However, dealing with ambiguous instructions in real-world environments remains a challenge for LLMs. Various methods for task ambiguity detection have been proposed. However, it is difficult to compare them because they are tested on different datasets and there is no universal benchmark. For this reason, we propose AmbiK (Ambiguous Tasks in Kitchen Environment), the fully textual dataset of ambiguous instructions addressed to a robot in a ki"},"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":"2506.04089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T15:47:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"b6672d136132d4c9a6ad9303afaeca5d8ba900316d3e7cfb1dc47d4d96fcf043","abstract_canon_sha256":"da0feeacc1f7f85b6e3fb606dd543b85c59ce915db637ac3f0e3b5919217e658"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:56.786168Z","signature_b64":"MEwyB+LlzBavqpaal2+wp1LLjwb48LTgnXxszzrguWHPiNT3Jf8L6GBBovMfvawD6zHF0ubnPsTJbGpfdRaEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7efffc585e6c93d6693f700d6b96c52ec3cde6a113e00bad9890fb353cb4997","last_reissued_at":"2026-07-05T11:15:56.785680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:56.785680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aleksandr I. Panov, Alexey K. Kovalev, Anastasiia Ivanova, Eva Bakaeva, Zoya Volovikova","submitted_at":"2025-06-04T15:47:07Z","abstract_excerpt":"As a part of an embodied agent, Large Language Models (LLMs) are typically used for behavior planning given natural language instructions from the user. However, dealing with ambiguous instructions in real-world environments remains a challenge for LLMs. Various methods for task ambiguity detection have been proposed. However, it is difficult to compare them because they are tested on different datasets and there is no universal benchmark. For this reason, we propose AmbiK (Ambiguous Tasks in Kitchen Environment), the fully textual dataset of ambiguous instructions addressed to a robot in a ki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04089","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/2506.04089/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":"2506.04089","created_at":"2026-07-05T11:15:56.785744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04089v1","created_at":"2026-07-05T11:15:56.785744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04089","created_at":"2026-07-05T11:15:56.785744+00:00"},{"alias_kind":"pith_short_12","alias_value":"47X77RMF43ET","created_at":"2026-07-05T11:15:56.785744+00:00"},{"alias_kind":"pith_short_16","alias_value":"47X77RMF43ET2ZUT","created_at":"2026-07-05T11:15:56.785744+00:00"},{"alias_kind":"pith_short_8","alias_value":"47X77RMF","created_at":"2026-07-05T11:15:56.785744+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/47X77RMF43ET2ZUT64ANNOLMKL","json":"https://pith.science/pith/47X77RMF43ET2ZUT64ANNOLMKL.json","graph_json":"https://pith.science/api/pith-number/47X77RMF43ET2ZUT64ANNOLMKL/graph.json","events_json":"https://pith.science/api/pith-number/47X77RMF43ET2ZUT64ANNOLMKL/events.json","paper":"https://pith.science/paper/47X77RMF"},"agent_actions":{"view_html":"https://pith.science/pith/47X77RMF43ET2ZUT64ANNOLMKL","download_json":"https://pith.science/pith/47X77RMF43ET2ZUT64ANNOLMKL.json","view_paper":"https://pith.science/paper/47X77RMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04089&json=true","fetch_graph":"https://pith.science/api/pith-number/47X77RMF43ET2ZUT64ANNOLMKL/graph.json","fetch_events":"https://pith.science/api/pith-number/47X77RMF43ET2ZUT64ANNOLMKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47X77RMF43ET2ZUT64ANNOLMKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47X77RMF43ET2ZUT64ANNOLMKL/action/storage_attestation","attest_author":"https://pith.science/pith/47X77RMF43ET2ZUT64ANNOLMKL/action/author_attestation","sign_citation":"https://pith.science/pith/47X77RMF43ET2ZUT64ANNOLMKL/action/citation_signature","submit_replication":"https://pith.science/pith/47X77RMF43ET2ZUT64ANNOLMKL/action/replication_record"}},"created_at":"2026-07-05T11:15:56.785744+00:00","updated_at":"2026-07-05T11:15:56.785744+00:00"}