{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4NQO37YDYICKRMKPURT6IEYG3K","short_pith_number":"pith:4NQO37YD","schema_version":"1.0","canonical_sha256":"e360edff03c204a8b14fa467e41306dabe095f468c471c2ea79ac79e1ce84ca1","source":{"kind":"arxiv","id":"2106.03427","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Joyce Chai, Yichi Zhang","submitted_at":"2021-06-07T08:48:44Z","abstract_excerpt":"Despite recent progress, learning new tasks through language instructions remains an extremely challenging problem. On the ALFRED benchmark for task learning, the published state-of-the-art system only achieves a task success rate of less than 10% in an unseen environment, compared to the human performance of over 90%. To address this issue, this paper takes a closer look at task learning. In a departure from a widely applied end-to-end architecture, we decomposed task learning into three sub-problems: sub-goal planning, scene navigation, and object manipulation; and developed a model HiTUT (s"},"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":"2106.03427","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-07T08:48:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"164018f7086ad88ba5339478912adc8e5deb80d1c62870bb16094b0100adbb08","abstract_canon_sha256":"5949333bfac772b3b55e5657027e13c8011367aa2bbe0fc892fb95e325e2e104"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:49.451667Z","signature_b64":"WJxk/kenHRf+y9rSs4iP8W3KBikccyCcCnksi7ycUygeTSwSLYmusXNtRk+7A72aFRVLkqRXZl+GxN9pGfxlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e360edff03c204a8b14fa467e41306dabe095f468c471c2ea79ac79e1ce84ca1","last_reissued_at":"2026-07-05T02:46:49.451227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:49.451227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Joyce Chai, Yichi Zhang","submitted_at":"2021-06-07T08:48:44Z","abstract_excerpt":"Despite recent progress, learning new tasks through language instructions remains an extremely challenging problem. On the ALFRED benchmark for task learning, the published state-of-the-art system only achieves a task success rate of less than 10% in an unseen environment, compared to the human performance of over 90%. To address this issue, this paper takes a closer look at task learning. In a departure from a widely applied end-to-end architecture, we decomposed task learning into three sub-problems: sub-goal planning, scene navigation, and object manipulation; and developed a model HiTUT (s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03427","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/2106.03427/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":"2106.03427","created_at":"2026-07-05T02:46:49.451288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03427v1","created_at":"2026-07-05T02:46:49.451288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03427","created_at":"2026-07-05T02:46:49.451288+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NQO37YDYICK","created_at":"2026-07-05T02:46:49.451288+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NQO37YDYICKRMKP","created_at":"2026-07-05T02:46:49.451288+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NQO37YD","created_at":"2026-07-05T02:46:49.451288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25851","citing_title":"RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19839","citing_title":"Environmental Understanding Vision-Language Model for Embodied Agent","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2303.03378","citing_title":"PaLM-E: An Embodied Multimodal Language Model","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14902","citing_title":"ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K","json":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K.json","graph_json":"https://pith.science/api/pith-number/4NQO37YDYICKRMKPURT6IEYG3K/graph.json","events_json":"https://pith.science/api/pith-number/4NQO37YDYICKRMKPURT6IEYG3K/events.json","paper":"https://pith.science/paper/4NQO37YD"},"agent_actions":{"view_html":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K","download_json":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K.json","view_paper":"https://pith.science/paper/4NQO37YD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03427&json=true","fetch_graph":"https://pith.science/api/pith-number/4NQO37YDYICKRMKPURT6IEYG3K/graph.json","fetch_events":"https://pith.science/api/pith-number/4NQO37YDYICKRMKPURT6IEYG3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K/action/storage_attestation","attest_author":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K/action/author_attestation","sign_citation":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K/action/citation_signature","submit_replication":"https://pith.science/pith/4NQO37YDYICKRMKPURT6IEYG3K/action/replication_record"}},"created_at":"2026-07-05T02:46:49.451288+00:00","updated_at":"2026-07-05T02:46:49.451288+00:00"}