{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4OFCYEEM7W7UUHFVCMUYIBGYTK","short_pith_number":"pith:4OFCYEEM","schema_version":"1.0","canonical_sha256":"e38a2c108cfdbf4a1cb513298404d89a8d98b71c82d92c2d53de53ea8a7082ce","source":{"kind":"arxiv","id":"2101.03431","version":1},"attestation_state":"computed","paper":{"title":"Are We There Yet? Learning to Localize in Embodied Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Gokhan Tur, Govind Thattai, Qiaozi Gao, Shane Storks","submitted_at":"2021-01-09T21:49:41Z","abstract_excerpt":"Embodied instruction following is a challenging problem requiring an agent to infer a sequence of primitive actions to achieve a goal environment state from complex language and visual inputs. Action Learning From Realistic Environments and Directives (ALFRED) is a recently proposed benchmark for this problem consisting of step-by-step natural language instructions to achieve subgoals which compose to an ultimate high-level goal. Key challenges for this task include localizing target locations and navigating to them through visual inputs, and grounding language instructions to visual appearanc"},"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":"2101.03431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-01-09T21:49:41Z","cross_cats_sorted":["cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"2c1ab979721fd753ba88ad9449d60144014369767e0a6d95be6c3deb709155c7","abstract_canon_sha256":"50a771aa5b5aaf61b2020de39305dde07e5091002e44142d506a25e78d3eed7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:50.153558Z","signature_b64":"x2CmGmLLrNP1s8DXEtyeYKfdiE3+We6A62GIymxAaKpTfHoLDZNGAOdQcMJ3phVrvmuA7+F6CCB7rcWurYsZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e38a2c108cfdbf4a1cb513298404d89a8d98b71c82d92c2d53de53ea8a7082ce","last_reissued_at":"2026-07-05T02:05:50.153202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:50.153202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are We There Yet? Learning to Localize in Embodied Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Gokhan Tur, Govind Thattai, Qiaozi Gao, Shane Storks","submitted_at":"2021-01-09T21:49:41Z","abstract_excerpt":"Embodied instruction following is a challenging problem requiring an agent to infer a sequence of primitive actions to achieve a goal environment state from complex language and visual inputs. Action Learning From Realistic Environments and Directives (ALFRED) is a recently proposed benchmark for this problem consisting of step-by-step natural language instructions to achieve subgoals which compose to an ultimate high-level goal. Key challenges for this task include localizing target locations and navigating to them through visual inputs, and grounding language instructions to visual appearanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03431","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/2101.03431/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":"2101.03431","created_at":"2026-07-05T02:05:50.153264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.03431v1","created_at":"2026-07-05T02:05:50.153264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03431","created_at":"2026-07-05T02:05:50.153264+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OFCYEEM7W7U","created_at":"2026-07-05T02:05:50.153264+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OFCYEEM7W7UUHFV","created_at":"2026-07-05T02:05:50.153264+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OFCYEEM","created_at":"2026-07-05T02:05:50.153264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK","json":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK.json","graph_json":"https://pith.science/api/pith-number/4OFCYEEM7W7UUHFVCMUYIBGYTK/graph.json","events_json":"https://pith.science/api/pith-number/4OFCYEEM7W7UUHFVCMUYIBGYTK/events.json","paper":"https://pith.science/paper/4OFCYEEM"},"agent_actions":{"view_html":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK","download_json":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK.json","view_paper":"https://pith.science/paper/4OFCYEEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.03431&json=true","fetch_graph":"https://pith.science/api/pith-number/4OFCYEEM7W7UUHFVCMUYIBGYTK/graph.json","fetch_events":"https://pith.science/api/pith-number/4OFCYEEM7W7UUHFVCMUYIBGYTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK/action/storage_attestation","attest_author":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK/action/author_attestation","sign_citation":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK/action/citation_signature","submit_replication":"https://pith.science/pith/4OFCYEEM7W7UUHFVCMUYIBGYTK/action/replication_record"}},"created_at":"2026-07-05T02:05:50.153264+00:00","updated_at":"2026-07-05T02:05:50.153264+00:00"}