{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TQEZR3IYSRMNH2OQC7LG35AULB","short_pith_number":"pith:TQEZR3IY","schema_version":"1.0","canonical_sha256":"9c0998ed189458d3e9d017d66df4145878700c8ce27ca444a89a6b935e72c4dc","source":{"kind":"arxiv","id":"2103.01991","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Environment Generation for Learning to Navigate the Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Honglak Lee, Izzeddin Gur, Kevin Malta, Manoj Tiwari, Natasha Jaques","submitted_at":"2021-03-02T19:19:30Z","abstract_excerpt":"Learning to autonomously navigate the web is a difficult sequential decision making task. The state and action spaces are large and combinatorial in nature, and websites are dynamic environments consisting of several pages. One of the bottlenecks of training web navigation agents is providing a learnable curriculum of training environments that can cover the large variety of real-world websites. Therefore, we propose using Adversarial Environment Generation (AEG) to generate challenging web environments in which to train reinforcement learning (RL) agents. We provide a new benchmarking environ"},"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":"2103.01991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T19:19:30Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"4b6b1c0daba831c84bcd971450a72f66cb16dac634903899bc15c9c1c78e67c3","abstract_canon_sha256":"6d7282ce2a4e6daf7932b645178ee0ebc5e3a8963e1e9289a0676bc76e754ab7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:59.232066Z","signature_b64":"ohttAbskzHcpYvCqDulbJO6CtqIn/EjUm6ttEfdRMkk4vw9Io3UZzYa/bU7ET71PKGfXsfcMXYmSmXmY1V3YAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c0998ed189458d3e9d017d66df4145878700c8ce27ca444a89a6b935e72c4dc","last_reissued_at":"2026-07-05T02:19:59.231560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:59.231560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Environment Generation for Learning to Navigate the Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Honglak Lee, Izzeddin Gur, Kevin Malta, Manoj Tiwari, Natasha Jaques","submitted_at":"2021-03-02T19:19:30Z","abstract_excerpt":"Learning to autonomously navigate the web is a difficult sequential decision making task. The state and action spaces are large and combinatorial in nature, and websites are dynamic environments consisting of several pages. One of the bottlenecks of training web navigation agents is providing a learnable curriculum of training environments that can cover the large variety of real-world websites. Therefore, we propose using Adversarial Environment Generation (AEG) to generate challenging web environments in which to train reinforcement learning (RL) agents. We provide a new benchmarking environ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01991","kind":"arxiv","version":1},"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/2103.01991/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":"2103.01991","created_at":"2026-07-05T02:19:59.231620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.01991v1","created_at":"2026-07-05T02:19:59.231620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01991","created_at":"2026-07-05T02:19:59.231620+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQEZR3IYSRMN","created_at":"2026-07-05T02:19:59.231620+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQEZR3IYSRMNH2OQ","created_at":"2026-07-05T02:19:59.231620+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQEZR3IY","created_at":"2026-07-05T02:19:59.231620+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":289,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06972","citing_title":"Differentiable Environment-Trajectory Co-Optimization for Safe Multi-Agent Navigation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB","json":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB.json","graph_json":"https://pith.science/api/pith-number/TQEZR3IYSRMNH2OQC7LG35AULB/graph.json","events_json":"https://pith.science/api/pith-number/TQEZR3IYSRMNH2OQC7LG35AULB/events.json","paper":"https://pith.science/paper/TQEZR3IY"},"agent_actions":{"view_html":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB","download_json":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB.json","view_paper":"https://pith.science/paper/TQEZR3IY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.01991&json=true","fetch_graph":"https://pith.science/api/pith-number/TQEZR3IYSRMNH2OQC7LG35AULB/graph.json","fetch_events":"https://pith.science/api/pith-number/TQEZR3IYSRMNH2OQC7LG35AULB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB/action/storage_attestation","attest_author":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB/action/author_attestation","sign_citation":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB/action/citation_signature","submit_replication":"https://pith.science/pith/TQEZR3IYSRMNH2OQC7LG35AULB/action/replication_record"}},"created_at":"2026-07-05T02:19:59.231620+00:00","updated_at":"2026-07-05T02:19:59.231620+00:00"}