{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BS46EDACA7LJ6E2A2RKKJ5OCXH","short_pith_number":"pith:BS46EDAC","schema_version":"1.0","canonical_sha256":"0cb9e20c0207d69f1340d454a4f5c2b9da29fded8c09547716f0d099f5ade154","source":{"kind":"arxiv","id":"1902.07257","version":1},"attestation_state":"computed","paper":{"title":"DOM-Q-NET: Grounded RL on Structured Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jamie Kiros, Jimmy Ba, Sheng Jia","submitted_at":"2019-02-19T19:54:15Z","abstract_excerpt":"Building agents to interact with the web would allow for significant improvements in knowledge understanding and representation learning. However, web navigation tasks are difficult for current deep reinforcement learning (RL) models due to the large discrete action space and the varying number of actions between the states. In this work, we introduce DOM-Q-NET, a novel architecture for RL-based web navigation to address both of these problems. It parametrizes Q functions with separate networks for different action categories: clicking a DOM element and typing a string input. Our model utilize"},"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":"1902.07257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T19:54:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1e9ac9e75b1ea8c0c2e1920e604d81ea9ff0a5a74422d97ff0f96f99323f1209","abstract_canon_sha256":"d60d49b45bf17db181fd819840f462daac0605df533f2d65ca4f949b891710f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:08.461560Z","signature_b64":"TuOwcTwNV1AY83pCaZqgC1IWzHebjGmWtLjntP97YIlnQwqfJJeZw0Nr45KBzSatQblMqXaxQv/CvGvx4WkGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cb9e20c0207d69f1340d454a4f5c2b9da29fded8c09547716f0d099f5ade154","last_reissued_at":"2026-05-17T23:53:08.461015Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:08.461015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DOM-Q-NET: Grounded RL on Structured Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jamie Kiros, Jimmy Ba, Sheng Jia","submitted_at":"2019-02-19T19:54:15Z","abstract_excerpt":"Building agents to interact with the web would allow for significant improvements in knowledge understanding and representation learning. However, web navigation tasks are difficult for current deep reinforcement learning (RL) models due to the large discrete action space and the varying number of actions between the states. In this work, we introduce DOM-Q-NET, a novel architecture for RL-based web navigation to address both of these problems. It parametrizes Q functions with separate networks for different action categories: clicking a DOM element and typing a string input. Our model utilize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07257","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":""},"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":"1902.07257","created_at":"2026-05-17T23:53:08.461097+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.07257v1","created_at":"2026-05-17T23:53:08.461097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07257","created_at":"2026-05-17T23:53:08.461097+00:00"},{"alias_kind":"pith_short_12","alias_value":"BS46EDACA7LJ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BS46EDACA7LJ6E2A","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BS46EDAC","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH","json":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH.json","graph_json":"https://pith.science/api/pith-number/BS46EDACA7LJ6E2A2RKKJ5OCXH/graph.json","events_json":"https://pith.science/api/pith-number/BS46EDACA7LJ6E2A2RKKJ5OCXH/events.json","paper":"https://pith.science/paper/BS46EDAC"},"agent_actions":{"view_html":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH","download_json":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH.json","view_paper":"https://pith.science/paper/BS46EDAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.07257&json=true","fetch_graph":"https://pith.science/api/pith-number/BS46EDACA7LJ6E2A2RKKJ5OCXH/graph.json","fetch_events":"https://pith.science/api/pith-number/BS46EDACA7LJ6E2A2RKKJ5OCXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH/action/storage_attestation","attest_author":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH/action/author_attestation","sign_citation":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH/action/citation_signature","submit_replication":"https://pith.science/pith/BS46EDACA7LJ6E2A2RKKJ5OCXH/action/replication_record"}},"created_at":"2026-05-17T23:53:08.461097+00:00","updated_at":"2026-05-17T23:53:08.461097+00:00"}