{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PRIUXRLVIHGLTUVF77NCQHQMR5","short_pith_number":"pith:PRIUXRLV","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"},"canonical_sha256":"7c514bc57541ccb9d2a5ffda281e0c8f61332bada209a2412ae734362b5d9776","source":{"kind":"arxiv","id":"2108.04927","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.04927","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"arxiv_version","alias_value":"2108.04927v2","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04927","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"pith_short_12","alias_value":"PRIUXRLVIHGL","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"pith_short_16","alias_value":"PRIUXRLVIHGLTUVF","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"pith_short_8","alias_value":"PRIUXRLV","created_at":"2026-07-05T03:29:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PRIUXRLVIHGLTUVF77NCQHQMR5","target":"record","payload":{"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"},"canonical_sha256":"7c514bc57541ccb9d2a5ffda281e0c8f61332bada209a2412ae734362b5d9776","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"},"source_kind":"arxiv","source_id":"2108.04927","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:29:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"McQryZRvDDhZmSr6Y7m63CypgnLftMv8lCERXJuxSqP0VybyoDDDa335kzkYCXVoWMN6mZsZjJKsy9NusNodDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:11:56.235778Z"},"content_sha256":"cad4d4e7bb633c5a7b9cd708a5d8bbcd8897ebce481787f7e7780347e53daf28","schema_version":"1.0","event_id":"sha256:cad4d4e7bb633c5a7b9cd708a5d8bbcd8897ebce481787f7e7780347e53daf28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PRIUXRLVIHGLTUVF77NCQHQMR5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:29:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6+FvvUIpdw1goVHCqg0b2XF+X2AivACduQhWuaYgLLV582SoCJ8XFPJKh8hYjrkwsHLOlQR2bFU5W2RszMzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:11:56.236174Z"},"content_sha256":"51c8ebb85f0790b3d55e5e492726a492dffc1094bb3745781beb2581866e83fa","schema_version":"1.0","event_id":"sha256:51c8ebb85f0790b3d55e5e492726a492dffc1094bb3745781beb2581866e83fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/bundle.json","state_url":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T04:11:56Z","links":{"resolver":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5","bundle":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/bundle.json","state":"https://pith.science/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRIUXRLVIHGLTUVF77NCQHQMR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PRIUXRLVIHGLTUVF77NCQHQMR5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e2078810b4822cf25e695dd58084b1fb2314ccf4f1eb90309d1875998966d622","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-10T21:24:05Z","title_canon_sha256":"faca7176114b2b650424de85bfb333aa7b61553fb217d2a22f00b89484932736"},"schema_version":"1.0","source":{"id":"2108.04927","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.04927","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"arxiv_version","alias_value":"2108.04927v2","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04927","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"pith_short_12","alias_value":"PRIUXRLVIHGL","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"pith_short_16","alias_value":"PRIUXRLVIHGLTUVF","created_at":"2026-07-05T03:29:03Z"},{"alias_kind":"pith_short_8","alias_value":"PRIUXRLV","created_at":"2026-07-05T03:29:03Z"}],"graph_snapshots":[{"event_id":"sha256:51c8ebb85f0790b3d55e5e492726a492dffc1094bb3745781beb2581866e83fa","target":"graph","created_at":"2026-07-05T03:29:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.04927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alessandro Suglia, Gaurav Sukhatme, Govind Thattai, Jesse Thomason, Qiaozi Gao","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-10T21:24:05Z","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04927","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cad4d4e7bb633c5a7b9cd708a5d8bbcd8897ebce481787f7e7780347e53daf28","target":"record","created_at":"2026-07-05T03:29:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e2078810b4822cf25e695dd58084b1fb2314ccf4f1eb90309d1875998966d622","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-10T21:24:05Z","title_canon_sha256":"faca7176114b2b650424de85bfb333aa7b61553fb217d2a22f00b89484932736"},"schema_version":"1.0","source":{"id":"2108.04927","kind":"arxiv","version":2}},"canonical_sha256":"7c514bc57541ccb9d2a5ffda281e0c8f61332bada209a2412ae734362b5d9776","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c514bc57541ccb9d2a5ffda281e0c8f61332bada209a2412ae734362b5d9776","first_computed_at":"2026-07-05T03:29:03.057927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:03.057927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pqRf9TS9iFf+rweypNuePqtbzXSUo+wjDySwsHbEsltfT21ZNJ4J7OcPqvXvxBL50MZOqi4agaOPGAZJ0WDNBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:03.058507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.04927","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cad4d4e7bb633c5a7b9cd708a5d8bbcd8897ebce481787f7e7780347e53daf28","sha256:51c8ebb85f0790b3d55e5e492726a492dffc1094bb3745781beb2581866e83fa"],"state_sha256":"2e6cd5634d631dd8df11835cc4fbefdf13af0aaf8658954eedfe4370445824a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/VvmvjM6ZW6eHkZ4HqOjSSJ1ZqMrS9/nJT+xEzLHHHF7C+g4c/CofTDHeDc/8STzv5nRSeI6pmNouYI1dV3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:11:56.239436Z","bundle_sha256":"1173c034402423b9741b20f7092a640a382dd14bb097bd7334249bafda31be9c"}}