{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SCLB5FDBIO4UKT5PUYTUNW3JRM","short_pith_number":"pith:SCLB5FDB","schema_version":"1.0","canonical_sha256":"90961e946143b9454fafa62746db698b08b4906960c8953b5c8d2641e30acf73","source":{"kind":"arxiv","id":"2002.10638","version":2},"attestation_state":"computed","paper":{"title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Jianfeng Gao, Lawrence Carin, Weituo Hao, Xiujun Li","submitted_at":"2020-02-25T03:08:12Z","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"},"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":"2002.10638","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-25T03:08:12Z","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"5b3be1a8d4c5dca2ccbf239837067536277890a21cca93b3467752ca66b372fd","abstract_canon_sha256":"51d96b27ba869244c37483b826c0c953bb60617961b56fd3f9fa0c13d53fb4f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:52.600055Z","signature_b64":"qROIDEEY+PZP6Jj6GdGHDbV99vqhaSkU2jz7NTzaEo+HyTO5vrG2HvrOB1EIz3GDTag1ju+MKW1TAzHAw3n7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90961e946143b9454fafa62746db698b08b4906960c8953b5c8d2641e30acf73","last_reissued_at":"2026-07-05T00:52:52.599679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:52.599679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Jianfeng Gao, Lawrence Carin, Weituo Hao, Xiujun Li","submitted_at":"2020-02-25T03:08:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10638","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/2002.10638/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":"2002.10638","created_at":"2026-07-05T00:52:52.599740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10638v2","created_at":"2026-07-05T00:52:52.599740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10638","created_at":"2026-07-05T00:52:52.599740+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCLB5FDBIO4U","created_at":"2026-07-05T00:52:52.599740+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCLB5FDBIO4UKT5P","created_at":"2026-07-05T00:52:52.599740+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCLB5FDB","created_at":"2026-07-05T00:52:52.599740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16516","citing_title":"Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM","json":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM.json","graph_json":"https://pith.science/api/pith-number/SCLB5FDBIO4UKT5PUYTUNW3JRM/graph.json","events_json":"https://pith.science/api/pith-number/SCLB5FDBIO4UKT5PUYTUNW3JRM/events.json","paper":"https://pith.science/paper/SCLB5FDB"},"agent_actions":{"view_html":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM","download_json":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM.json","view_paper":"https://pith.science/paper/SCLB5FDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10638&json=true","fetch_graph":"https://pith.science/api/pith-number/SCLB5FDBIO4UKT5PUYTUNW3JRM/graph.json","fetch_events":"https://pith.science/api/pith-number/SCLB5FDBIO4UKT5PUYTUNW3JRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM/action/storage_attestation","attest_author":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM/action/author_attestation","sign_citation":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM/action/citation_signature","submit_replication":"https://pith.science/pith/SCLB5FDBIO4UKT5PUYTUNW3JRM/action/replication_record"}},"created_at":"2026-07-05T00:52:52.599740+00:00","updated_at":"2026-07-05T00:52:52.599740+00:00"}