{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SCLB5FDBIO4UKT5PUYTUNW3JRM","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":"51d96b27ba869244c37483b826c0c953bb60617961b56fd3f9fa0c13d53fb4f7","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-25T03:08:12Z","title_canon_sha256":"5b3be1a8d4c5dca2ccbf239837067536277890a21cca93b3467752ca66b372fd"},"schema_version":"1.0","source":{"id":"2002.10638","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.10638","created_at":"2026-07-05T00:52:52Z"},{"alias_kind":"arxiv_version","alias_value":"2002.10638v2","created_at":"2026-07-05T00:52:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10638","created_at":"2026-07-05T00:52:52Z"},{"alias_kind":"pith_short_12","alias_value":"SCLB5FDBIO4U","created_at":"2026-07-05T00:52:52Z"},{"alias_kind":"pith_short_16","alias_value":"SCLB5FDBIO4UKT5P","created_at":"2026-07-05T00:52:52Z"},{"alias_kind":"pith_short_8","alias_value":"SCLB5FDB","created_at":"2026-07-05T00:52:52Z"}],"graph_snapshots":[{"event_id":"sha256:bfc0661b3fac575055f9fc19acf238bea85cf3bb48253c83a05591576914b77c","target":"graph","created_at":"2026-07-05T00:52:52Z","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/2002.10638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper, we present the first pre-training and fine-tuning paradigm for vision-and-language navigation (VLN) tasks. By training on a large amount of image-text-action triplets in a self-supervised learning manner, the pre-trained model provides generic representations of visual environments and language instructions. It can be easily used as a drop-in for existing V","authors_text":"Chunyuan Li, Jianfeng Gao, Lawrence Carin, Weituo Hao, Xiujun Li","cross_cats":["cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-25T03:08:12Z","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10638","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:a64167851a30e07a5cec8430e3ca91885ed71f8aeacbdbe1c807ce9ecc27f681","target":"record","created_at":"2026-07-05T00:52:52Z","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":"51d96b27ba869244c37483b826c0c953bb60617961b56fd3f9fa0c13d53fb4f7","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-25T03:08:12Z","title_canon_sha256":"5b3be1a8d4c5dca2ccbf239837067536277890a21cca93b3467752ca66b372fd"},"schema_version":"1.0","source":{"id":"2002.10638","kind":"arxiv","version":2}},"canonical_sha256":"90961e946143b9454fafa62746db698b08b4906960c8953b5c8d2641e30acf73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90961e946143b9454fafa62746db698b08b4906960c8953b5c8d2641e30acf73","first_computed_at":"2026-07-05T00:52:52.599679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:52.599679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qROIDEEY+PZP6Jj6GdGHDbV99vqhaSkU2jz7NTzaEo+HyTO5vrG2HvrOB1EIz3GDTag1ju+MKW1TAzHAw3n7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:52.600055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.10638","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a64167851a30e07a5cec8430e3ca91885ed71f8aeacbdbe1c807ce9ecc27f681","sha256:bfc0661b3fac575055f9fc19acf238bea85cf3bb48253c83a05591576914b77c"],"state_sha256":"5de54fc2a209982027a088f3afbdbcbca97bfaef0b06d65efc969eb3a43074bc"}