{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QLTOIQCVWWCWGTDAYCOQMWJPP7","short_pith_number":"pith:QLTOIQCV","schema_version":"1.0","canonical_sha256":"82e6e44055b585634c60c09d06592f7fffa4ddcc53c5dff87f3a4146a1ea11d6","source":{"kind":"arxiv","id":"2401.02991","version":1},"attestation_state":"computed","paper":{"title":"GLIDE-RL: Grounded Language Instruction through DEmonstration in RL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chaitanya Kharyal, Matthew E. Taylor, Sai Krishna Gottipati, Srijita Das, Tanmay Kumar Sinha","submitted_at":"2024-01-03T17:32:13Z","abstract_excerpt":"One of the final frontiers in the development of complex human - AI collaborative systems is the ability of AI agents to comprehend the natural language and perform tasks accordingly. However, training efficient Reinforcement Learning (RL) agents grounded in natural language has been a long-standing challenge due to the complexity and ambiguity of the language and sparsity of the rewards, among other factors. Several advances in reinforcement learning, curriculum learning, continual learning, language models have independently contributed to effective training of grounded agents in various env"},"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":"2401.02991","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-03T17:32:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"74a14d58cc470bf65d4ed623e1365279b31e6ec17246f417398115b4c781b54d","abstract_canon_sha256":"c8de043c68d9f7b4c4feaf53300f5134298835ec56d7467afebc42795a6571c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:00.588866Z","signature_b64":"FfmLadI4nH/OcAXLWIwOt4Wk6U92pQZdHra5F9r8cxXHkEqIHoye1+jugVR1XQILg4Y6hGo0XiITNzsMT3kzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82e6e44055b585634c60c09d06592f7fffa4ddcc53c5dff87f3a4146a1ea11d6","last_reissued_at":"2026-07-05T07:31:00.588389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:00.588389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLIDE-RL: Grounded Language Instruction through DEmonstration in RL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chaitanya Kharyal, Matthew E. Taylor, Sai Krishna Gottipati, Srijita Das, Tanmay Kumar Sinha","submitted_at":"2024-01-03T17:32:13Z","abstract_excerpt":"One of the final frontiers in the development of complex human - AI collaborative systems is the ability of AI agents to comprehend the natural language and perform tasks accordingly. However, training efficient Reinforcement Learning (RL) agents grounded in natural language has been a long-standing challenge due to the complexity and ambiguity of the language and sparsity of the rewards, among other factors. Several advances in reinforcement learning, curriculum learning, continual learning, language models have independently contributed to effective training of grounded agents in various env"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02991","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/2401.02991/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":"2401.02991","created_at":"2026-07-05T07:31:00.588450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02991v1","created_at":"2026-07-05T07:31:00.588450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02991","created_at":"2026-07-05T07:31:00.588450+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLTOIQCVWWCW","created_at":"2026-07-05T07:31:00.588450+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLTOIQCVWWCWGTDA","created_at":"2026-07-05T07:31:00.588450+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLTOIQCV","created_at":"2026-07-05T07:31:00.588450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24729","citing_title":"SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7","json":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7.json","graph_json":"https://pith.science/api/pith-number/QLTOIQCVWWCWGTDAYCOQMWJPP7/graph.json","events_json":"https://pith.science/api/pith-number/QLTOIQCVWWCWGTDAYCOQMWJPP7/events.json","paper":"https://pith.science/paper/QLTOIQCV"},"agent_actions":{"view_html":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7","download_json":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7.json","view_paper":"https://pith.science/paper/QLTOIQCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02991&json=true","fetch_graph":"https://pith.science/api/pith-number/QLTOIQCVWWCWGTDAYCOQMWJPP7/graph.json","fetch_events":"https://pith.science/api/pith-number/QLTOIQCVWWCWGTDAYCOQMWJPP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7/action/storage_attestation","attest_author":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7/action/author_attestation","sign_citation":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7/action/citation_signature","submit_replication":"https://pith.science/pith/QLTOIQCVWWCWGTDAYCOQMWJPP7/action/replication_record"}},"created_at":"2026-07-05T07:31:00.588450+00:00","updated_at":"2026-07-05T07:31:00.588450+00:00"}