{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MW5EHOILRBE7YZNOAMTWENHBPG","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":"3b730f6e839934803da65ec916878bf03f79311641af6487b3738cc1acc5ea10","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T17:59:07Z","title_canon_sha256":"7f7925e9bec4d2708b827bbd2995630117245991c3417113f99589566ccd9f98"},"schema_version":"1.0","source":{"id":"2103.16561","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16561","created_at":"2026-07-05T04:20:14Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16561v2","created_at":"2026-07-05T04:20:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16561","created_at":"2026-07-05T04:20:14Z"},{"alias_kind":"pith_short_12","alias_value":"MW5EHOILRBE7","created_at":"2026-07-05T04:20:14Z"},{"alias_kind":"pith_short_16","alias_value":"MW5EHOILRBE7YZNO","created_at":"2026-07-05T04:20:14Z"},{"alias_kind":"pith_short_8","alias_value":"MW5EHOIL","created_at":"2026-07-05T04:20:14Z"}],"graph_snapshots":[{"event_id":"sha256:ef6944af44c624f3b698480865e9000012795b74411e92e441da23e76aa44798","target":"graph","created_at":"2026-07-05T04:20:14Z","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/2103.16561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-language navigation (VLN) is a multimodal task where an agent follows natural language instructions and navigates in visual environments. Multiple setups have been proposed, and researchers apply new model architectures or training techniques to boost navigation performance. However, there still exist non-negligible gaps between machines' performance and human benchmarks. Moreover, the agents' inner mechanisms for navigation decisions remain unclear. To the best of our knowledge, how the agents perceive the multimodal input is under-studied and needs investigation. In this work, we ","authors_text":"Kazoo Sone, Miguel Eckstein, Pradyumna Narayana, Qi Wu, Sugato Basu, Wanrong Zhu, William Yang Wang, Xin Eric Wang, Yuankai Qi","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T17:59:07Z","title":"Diagnosing Vision-and-Language Navigation: What Really Matters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16561","kind":"arxiv","version":2},"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":"sha256:63f91e55864694992c6bca69399d4b9687b74ef2044e9222762ffaf832c46067","target":"record","created_at":"2026-07-05T04:20:14Z","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":"3b730f6e839934803da65ec916878bf03f79311641af6487b3738cc1acc5ea10","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T17:59:07Z","title_canon_sha256":"7f7925e9bec4d2708b827bbd2995630117245991c3417113f99589566ccd9f98"},"schema_version":"1.0","source":{"id":"2103.16561","kind":"arxiv","version":2}},"canonical_sha256":"65ba43b90b8849fc65ae03276234e179b2cc8b1976a639abe4c1722c13e7ed73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65ba43b90b8849fc65ae03276234e179b2cc8b1976a639abe4c1722c13e7ed73","first_computed_at":"2026-07-05T04:20:14.509959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:14.509959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3i28rgKk1Iv9vW4YSifZKqHuaAWZIH0LZ5OIR6sMF5DrzrwViEK3ZsfDCzvcMnop6qfO9prLUGjjaCNN6YaNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:14.510455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.16561","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63f91e55864694992c6bca69399d4b9687b74ef2044e9222762ffaf832c46067","sha256:ef6944af44c624f3b698480865e9000012795b74411e92e441da23e76aa44798"],"state_sha256":"6cb8e43c1c104a462529aaff652fdc1df766bad6e7f8883f88a749ab18116b1c"}