{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YP7YTWYOSVOBZZNGN53QJX4CTP","short_pith_number":"pith:YP7YTWYO","schema_version":"1.0","canonical_sha256":"c3ff89db0e955c1ce5a66f7704df829bec8ca7e5ae78d7e1037a041636511dba","source":{"kind":"arxiv","id":"1810.08272","version":4},"attestation_state":"computed","paper":{"title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chitwan Saharia, Dzmitry Bahdanau, Lucas Willems, Maxime Chevalier-Boisvert, Salem Lahlou, Thien Huu Nguyen, Yoshua Bengio","submitted_at":"2018-10-18T20:48:08Z","abstract_excerpt":"Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language whi"},"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":"1810.08272","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-18T20:48:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f6dd323f9805746f5d41abf81ed5863941bae9d408354a9d15da04f51420cad6","abstract_canon_sha256":"d18d874b2bb4f90760f49c325fb2aef0b748b0be0621513ba26ea8b30b6a11a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:14.771709Z","signature_b64":"cNW/nNXD7XOP+3Pn0noQc2LaNQgKSXXxPeqig+fTR2YVMGMyddRV6iIZ/iwunOu66rRwPKDenbqSn5X02EtyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3ff89db0e955c1ce5a66f7704df829bec8ca7e5ae78d7e1037a041636511dba","last_reissued_at":"2026-07-05T00:27:14.770499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:14.770499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chitwan Saharia, Dzmitry Bahdanau, Lucas Willems, Maxime Chevalier-Boisvert, Salem Lahlou, Thien Huu Nguyen, Yoshua Bengio","submitted_at":"2018-10-18T20:48:08Z","abstract_excerpt":"Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08272","kind":"arxiv","version":4},"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/1810.08272/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":"1810.08272","created_at":"2026-07-05T00:27:14.770604+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.08272v4","created_at":"2026-07-05T00:27:14.770604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08272","created_at":"2026-07-05T00:27:14.770604+00:00"},{"alias_kind":"pith_short_12","alias_value":"YP7YTWYOSVOB","created_at":"2026-07-05T00:27:14.770604+00:00"},{"alias_kind":"pith_short_16","alias_value":"YP7YTWYOSVOBZZNG","created_at":"2026-07-05T00:27:14.770604+00:00"},{"alias_kind":"pith_short_8","alias_value":"YP7YTWYO","created_at":"2026-07-05T00:27:14.770604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24622","citing_title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24828","citing_title":"Test-Time Deep Thinking to Explore Implicit Rules","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"1907.08584","citing_title":"CraftAssist: A Framework for Dialogue-enabled Interactive Agents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"1907.09273","citing_title":"Why Build an Assistant in Minecraft?","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2402.05284","citing_title":"Analyzing Adversarial Inputs in Deep Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05044","citing_title":"WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2205.06175","citing_title":"A Generalist Agent","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24729","citing_title":"SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20601","citing_title":"Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP","json":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP.json","graph_json":"https://pith.science/api/pith-number/YP7YTWYOSVOBZZNGN53QJX4CTP/graph.json","events_json":"https://pith.science/api/pith-number/YP7YTWYOSVOBZZNGN53QJX4CTP/events.json","paper":"https://pith.science/paper/YP7YTWYO"},"agent_actions":{"view_html":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP","download_json":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP.json","view_paper":"https://pith.science/paper/YP7YTWYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.08272&json=true","fetch_graph":"https://pith.science/api/pith-number/YP7YTWYOSVOBZZNGN53QJX4CTP/graph.json","fetch_events":"https://pith.science/api/pith-number/YP7YTWYOSVOBZZNGN53QJX4CTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP/action/storage_attestation","attest_author":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP/action/author_attestation","sign_citation":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP/action/citation_signature","submit_replication":"https://pith.science/pith/YP7YTWYOSVOBZZNGN53QJX4CTP/action/replication_record"}},"created_at":"2026-07-05T00:27:14.770604+00:00","updated_at":"2026-07-05T00:27:14.770604+00:00"}