{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WKZ2KIJK53GMFGOBVLSG5FNKWZ","short_pith_number":"pith:WKZ2KIJK","schema_version":"1.0","canonical_sha256":"b2b3a5212aeeccc299c1aae46e95aab670a6518b3a427df3fc4cba3944b56d7f","source":{"kind":"arxiv","id":"1907.05446","version":2},"attestation_state":"computed","paper":{"title":"General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Alexander Ku, Eugene Ie, Gabriel Ilharco, Jason Baldridge, Vihan Jain","submitted_at":"2019-07-11T18:42:03Z","abstract_excerpt":"In instruction conditioned navigation, agents interpret natural language and their surroundings to navigate through an environment. Datasets for studying this task typically contain pairs of these instructions and reference trajectories. Yet, most evaluation metrics used thus far fail to properly account for the latter, relying instead on insufficient similarity comparisons. We address fundamental flaws in previously used metrics and show how Dynamic Time Warping (DTW), a long known method of measuring similarity between two time series, can be used for evaluation of navigation agents. For suc"},"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":"1907.05446","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-07-11T18:42:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3a78ed6d25b0baf881fdf9beef64cdadfe3602a6f5aeefe24763fb2acae18888","abstract_canon_sha256":"dbd761aec35b41e2cf7bcb4be4981bf5f6ae67467d9a4696c7cecf50cf25a648"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:40.722047Z","signature_b64":"3DjThbifBkwJqlpQ37KebGR1SoUhG1eSM7IVV7JOOcXzJYxmJLizF+54xd+lFaun607tfD8r7yieyxQW/V/nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b3a5212aeeccc299c1aae46e95aab670a6518b3a427df3fc4cba3944b56d7f","last_reissued_at":"2026-07-05T00:22:40.721563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:40.721563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Alexander Ku, Eugene Ie, Gabriel Ilharco, Jason Baldridge, Vihan Jain","submitted_at":"2019-07-11T18:42:03Z","abstract_excerpt":"In instruction conditioned navigation, agents interpret natural language and their surroundings to navigate through an environment. Datasets for studying this task typically contain pairs of these instructions and reference trajectories. Yet, most evaluation metrics used thus far fail to properly account for the latter, relying instead on insufficient similarity comparisons. We address fundamental flaws in previously used metrics and show how Dynamic Time Warping (DTW), a long known method of measuring similarity between two time series, can be used for evaluation of navigation agents. For suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05446","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/1907.05446/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":"1907.05446","created_at":"2026-07-05T00:22:40.721622+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05446v2","created_at":"2026-07-05T00:22:40.721622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05446","created_at":"2026-07-05T00:22:40.721622+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKZ2KIJK53GM","created_at":"2026-07-05T00:22:40.721622+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKZ2KIJK53GMFGOB","created_at":"2026-07-05T00:22:40.721622+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKZ2KIJK","created_at":"2026-07-05T00:22:40.721622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30151","citing_title":"AERIS: Aerial-Edge Role-Driven Intelligence at Runtime via Orchestrated Language-Model Swarm","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22816","citing_title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ","json":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ.json","graph_json":"https://pith.science/api/pith-number/WKZ2KIJK53GMFGOBVLSG5FNKWZ/graph.json","events_json":"https://pith.science/api/pith-number/WKZ2KIJK53GMFGOBVLSG5FNKWZ/events.json","paper":"https://pith.science/paper/WKZ2KIJK"},"agent_actions":{"view_html":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ","download_json":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ.json","view_paper":"https://pith.science/paper/WKZ2KIJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05446&json=true","fetch_graph":"https://pith.science/api/pith-number/WKZ2KIJK53GMFGOBVLSG5FNKWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WKZ2KIJK53GMFGOBVLSG5FNKWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ/action/storage_attestation","attest_author":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ/action/author_attestation","sign_citation":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ/action/citation_signature","submit_replication":"https://pith.science/pith/WKZ2KIJK53GMFGOBVLSG5FNKWZ/action/replication_record"}},"created_at":"2026-07-05T00:22:40.721622+00:00","updated_at":"2026-07-05T00:22:40.721622+00:00"}