{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DVWILF4P3EZ7SLYKVLGSPT327C","short_pith_number":"pith:DVWILF4P","schema_version":"1.0","canonical_sha256":"1d6c85978fd933f92f0aaacd27cf7af89b73463c60488a31645fca2901f43f5e","source":{"kind":"arxiv","id":"2005.00811","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Kartik Talamadupula, Keerthiram Murugesan, Mattia Atzeni, Mrinmaya Sachan, Pavan Kapanipathi, Pushkar Shukla","submitted_at":"2020-05-02T12:07:02Z","abstract_excerpt":"In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments. This reliance on text brings advances in natural language processing into the ambit of these agents, with a recurring thread being the use of external knowledge to mimic and better human-level performance. We present one such instantiation of agents that use commonsense knowledge from ConceptNet to show promising performance on two text-based environments."},"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":"2005.00811","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-05-02T12:07:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"af527e4f13054242f44ecdb5eeb35057f727e28f3059625b694bbff84128a2a9","abstract_canon_sha256":"66a4544116b671a55e55493eca18353802bc9f917331a6ffa5cac578f3c40c8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:00.986730Z","signature_b64":"V0lcQszG20Rg867uOpOfhc6oeK0seoYyly3bvBuME2fy9IQ3Fj/qu6mNdQOG/Yfe7AxcxZ5NNaJDfARed5fEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d6c85978fd933f92f0aaacd27cf7af89b73463c60488a31645fca2901f43f5e","last_reissued_at":"2026-07-05T01:00:00.986372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:00.986372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Kartik Talamadupula, Keerthiram Murugesan, Mattia Atzeni, Mrinmaya Sachan, Pavan Kapanipathi, Pushkar Shukla","submitted_at":"2020-05-02T12:07:02Z","abstract_excerpt":"In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments. This reliance on text brings advances in natural language processing into the ambit of these agents, with a recurring thread being the use of external knowledge to mimic and better human-level performance. We present one such instantiation of agents that use commonsense knowledge from ConceptNet to show promising performance on two text-based environments."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00811","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/2005.00811/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":"2005.00811","created_at":"2026-07-05T01:00:00.986431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00811v1","created_at":"2026-07-05T01:00:00.986431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00811","created_at":"2026-07-05T01:00:00.986431+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVWILF4P3EZ7","created_at":"2026-07-05T01:00:00.986431+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVWILF4P3EZ7SLYK","created_at":"2026-07-05T01:00:00.986431+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVWILF4P","created_at":"2026-07-05T01:00:00.986431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09331","citing_title":"Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation","ref_index":85,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C","json":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C.json","graph_json":"https://pith.science/api/pith-number/DVWILF4P3EZ7SLYKVLGSPT327C/graph.json","events_json":"https://pith.science/api/pith-number/DVWILF4P3EZ7SLYKVLGSPT327C/events.json","paper":"https://pith.science/paper/DVWILF4P"},"agent_actions":{"view_html":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C","download_json":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C.json","view_paper":"https://pith.science/paper/DVWILF4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00811&json=true","fetch_graph":"https://pith.science/api/pith-number/DVWILF4P3EZ7SLYKVLGSPT327C/graph.json","fetch_events":"https://pith.science/api/pith-number/DVWILF4P3EZ7SLYKVLGSPT327C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C/action/storage_attestation","attest_author":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C/action/author_attestation","sign_citation":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C/action/citation_signature","submit_replication":"https://pith.science/pith/DVWILF4P3EZ7SLYKVLGSPT327C/action/replication_record"}},"created_at":"2026-07-05T01:00:00.986431+00:00","updated_at":"2026-07-05T01:00:00.986431+00:00"}