{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PRIUXRLVIHGLTUVF77NCQHQMR5","short_pith_number":"pith:PRIUXRLV","schema_version":"1.0","canonical_sha256":"7c514bc57541ccb9d2a5ffda281e0c8f61332bada209a2412ae734362b5d9776","source":{"kind":"arxiv","id":"2108.04927","version":2},"attestation_state":"computed","paper":{"title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessandro Suglia, Gaurav Sukhatme, Govind Thattai, Jesse Thomason, Qiaozi Gao","submitted_at":"2021-08-10T21:24:05Z","abstract_excerpt":"Language-guided robots performing home and office tasks must navigate in and interact with the world. Grounding language instructions against visual observations and actions to take in an environment is an open challenge. We present Embodied BERT (EmBERT), a transformer-based model which can attend to high-dimensional, multi-modal inputs across long temporal horizons for language-conditioned task completion. Additionally, we bridge the gap between successful object-centric navigation models used for non-interactive agents and the language-guided visual task completion benchmark, ALFRED, by int"},"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":"2108.04927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-10T21:24:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"faca7176114b2b650424de85bfb333aa7b61553fb217d2a22f00b89484932736","abstract_canon_sha256":"e2078810b4822cf25e695dd58084b1fb2314ccf4f1eb90309d1875998966d622"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:03.058507Z","signature_b64":"pqRf9TS9iFf+rweypNuePqtbzXSUo+wjDySwsHbEsltfT21ZNJ4J7OcPqvXvxBL50MZOqi4agaOPGAZJ0WDNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c514bc57541ccb9d2a5ffda281e0c8f61332bada209a2412ae734362b5d9776","last_reissued_at":"2026-07-05T03:29:03.057927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:03.057927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessandro Suglia, Gaurav Sukhatme, Govind Thattai, Jesse Thomason, Qiaozi Gao","submitted_at":"2021-08-10T21:24:05Z","abstract_excerpt":"Language-guided robots performing home and office tasks must navigate in and interact with the world. Grounding language instructions against visual observations and actions to take in an environment is an open challenge. We present Embodied BERT (EmBERT), a transformer-based model which can attend to high-dimensional, multi-modal inputs across long temporal horizons for language-conditioned task completion. Additionally, we bridge the gap between successful object-centric navigation models used for non-interactive agents and the language-guided visual task completion benchmark, ALFRED, by int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04927","kind":"arxiv","version":2},"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/2108.04927/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":"2108.04927","created_at":"2026-07-05T03:29:03.057991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04927v2","created_at":"2026-07-05T03:29:03.057991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04927","created_at":"2026-07-05T03:29:03.057991+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRIUXRLVIHGL","created_at":"2026-07-05T03:29:03.057991+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRIUXRLVIHGLTUVF","created_at":"2026-07-05T03:29:03.057991+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRIUXRLV","created_at":"2026-07-05T03:29:03.057991+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":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30231","citing_title":"Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05608","citing_title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5","json":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5.json","graph_json":"https://pith.science/api/pith-number/PRIUXRLVIHGLTUVF77NCQHQMR5/graph.json","events_json":"https://pith.science/api/pith-number/PRIUXRLVIHGLTUVF77NCQHQMR5/events.json","paper":"https://pith.science/paper/PRIUXRLV"},"agent_actions":{"view_html":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5","download_json":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5.json","view_paper":"https://pith.science/paper/PRIUXRLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04927&json=true","fetch_graph":"https://pith.science/api/pith-number/PRIUXRLVIHGLTUVF77NCQHQMR5/graph.json","fetch_events":"https://pith.science/api/pith-number/PRIUXRLVIHGLTUVF77NCQHQMR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/action/storage_attestation","attest_author":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/action/author_attestation","sign_citation":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/action/citation_signature","submit_replication":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/action/replication_record"}},"created_at":"2026-07-05T03:29:03.057991+00:00","updated_at":"2026-07-05T03:29:03.057991+00:00"}