{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KLBADOWH27JX6UNDPBDNQ5EM24","short_pith_number":"pith:KLBADOWH","schema_version":"1.0","canonical_sha256":"52c201bac7d7d37f51a37846d8748cd72ed41cf49c02e59d9b00b0abf761b71f","source":{"kind":"arxiv","id":"2105.09637","version":2},"attestation_state":"computed","paper":{"title":"Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ali Shaw, Evelyn Zuniga, Gavin Costello, Guy Leroy, Ida Momennejad, Jaroslaw Rzepecki, Katja Hofmann, Raluca Georgescu, Sam Devlin","submitted_at":"2021-05-20T10:14:23Z","abstract_excerpt":"A key challenge on the path to developing agents that learn complex human-like behavior is the need to quickly and accurately quantify human-likeness. While human assessments of such behavior can be highly accurate, speed and scalability are limited. We address these limitations through a novel automated Navigation Turing Test (ANTT) that learns to predict human judgments of human-likeness. We demonstrate the effectiveness of our automated NTT on a navigation task in a complex 3D environment. We investigate six classification models to shed light on the types of architectures best suited to 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":"2105.09637","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-20T10:14:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"90b4ec3529e6f1113a5a06a811f5970d025c4d8d363882b1591defba678454f3","abstract_canon_sha256":"4af4fc9340fce08685baab7e9d760e8a1958ecee81e1d84e1511471844b94059"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:01:24.339492Z","signature_b64":"K5+anptFmbOeh5XIWaJS4XEO4Yha/7oW3ERs3LdBf4TJ4cDRr22INSZnd9dR+rg+gL5yPtbiCWjEHGYqITgNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c201bac7d7d37f51a37846d8748cd72ed41cf49c02e59d9b00b0abf761b71f","last_reissued_at":"2026-07-05T03:01:24.339107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:01:24.339107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ali Shaw, Evelyn Zuniga, Gavin Costello, Guy Leroy, Ida Momennejad, Jaroslaw Rzepecki, Katja Hofmann, Raluca Georgescu, Sam Devlin","submitted_at":"2021-05-20T10:14:23Z","abstract_excerpt":"A key challenge on the path to developing agents that learn complex human-like behavior is the need to quickly and accurately quantify human-likeness. While human assessments of such behavior can be highly accurate, speed and scalability are limited. We address these limitations through a novel automated Navigation Turing Test (ANTT) that learns to predict human judgments of human-likeness. We demonstrate the effectiveness of our automated NTT on a navigation task in a complex 3D environment. We investigate six classification models to shed light on the types of architectures best suited to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09637","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/2105.09637/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":"2105.09637","created_at":"2026-07-05T03:01:24.339163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.09637v2","created_at":"2026-07-05T03:01:24.339163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09637","created_at":"2026-07-05T03:01:24.339163+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLBADOWH27JX","created_at":"2026-07-05T03:01:24.339163+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLBADOWH27JX6UND","created_at":"2026-07-05T03:01:24.339163+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLBADOWH","created_at":"2026-07-05T03:01:24.339163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07177","citing_title":"Effective Reward Specification in Deep Reinforcement Learning","ref_index":83,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24","json":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24.json","graph_json":"https://pith.science/api/pith-number/KLBADOWH27JX6UNDPBDNQ5EM24/graph.json","events_json":"https://pith.science/api/pith-number/KLBADOWH27JX6UNDPBDNQ5EM24/events.json","paper":"https://pith.science/paper/KLBADOWH"},"agent_actions":{"view_html":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24","download_json":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24.json","view_paper":"https://pith.science/paper/KLBADOWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.09637&json=true","fetch_graph":"https://pith.science/api/pith-number/KLBADOWH27JX6UNDPBDNQ5EM24/graph.json","fetch_events":"https://pith.science/api/pith-number/KLBADOWH27JX6UNDPBDNQ5EM24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24/action/storage_attestation","attest_author":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24/action/author_attestation","sign_citation":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24/action/citation_signature","submit_replication":"https://pith.science/pith/KLBADOWH27JX6UNDPBDNQ5EM24/action/replication_record"}},"created_at":"2026-07-05T03:01:24.339163+00:00","updated_at":"2026-07-05T03:01:24.339163+00:00"}