{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MOAOUI5ZPJVSKWATO7LND7YOG4","short_pith_number":"pith:MOAOUI5Z","canonical_record":{"source":{"id":"2109.02161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-05T20:11:53Z","cross_cats_sorted":[],"title_canon_sha256":"c42e1d1e86cd8507ab6b0e89bf57c9066ea3d838bf61cbb6a69f288e31e3dbc1","abstract_canon_sha256":"ba6ccdaaf268d1c68a2653e769068eae3eba58083297b609d9c5d34fd7b5678f"},"schema_version":"1.0"},"canonical_sha256":"6380ea23b97a6b25581377d6d1ff0e3710315593014971535a85b7ae556c53e6","source":{"kind":"arxiv","id":"2109.02161","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02161","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02161v1","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02161","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"pith_short_12","alias_value":"MOAOUI5ZPJVS","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"pith_short_16","alias_value":"MOAOUI5ZPJVSKWAT","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"pith_short_8","alias_value":"MOAOUI5Z","created_at":"2026-07-05T03:11:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MOAOUI5ZPJVSKWATO7LND7YOG4","target":"record","payload":{"canonical_record":{"source":{"id":"2109.02161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-05T20:11:53Z","cross_cats_sorted":[],"title_canon_sha256":"c42e1d1e86cd8507ab6b0e89bf57c9066ea3d838bf61cbb6a69f288e31e3dbc1","abstract_canon_sha256":"ba6ccdaaf268d1c68a2653e769068eae3eba58083297b609d9c5d34fd7b5678f"},"schema_version":"1.0"},"canonical_sha256":"6380ea23b97a6b25581377d6d1ff0e3710315593014971535a85b7ae556c53e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:39.461286Z","signature_b64":"5qlRCuk0r02TIytzDIvxeCQBZImtghaAtdS7sB8d8R7RarS8bkakzPc/ApylTcM4pwWCcE/6qiQjFMnm2sTdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6380ea23b97a6b25581377d6d1ff0e3710315593014971535a85b7ae556c53e6","last_reissued_at":"2026-07-05T03:11:39.460897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:39.460897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.02161","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:11:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OZEkv4IUtNerePqB99MSe1bBKbsgCZ5xB1LfeRCKrm82ls3ew+I3JLMS+ZYcTTjpnhh/ZneEahE3UMzwTNN8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T06:21:03.510797Z"},"content_sha256":"7cb075b9e9c011e51890b8b832690daa62ff58226256bc8fd9ec18aee491f167","schema_version":"1.0","event_id":"sha256:7cb075b9e9c011e51890b8b832690daa62ff58226256bc8fd9ec18aee491f167"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MOAOUI5ZPJVSKWATO7LND7YOG4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modular Framework for Visuomotor Language Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Charless C. Fowlkes, Daeyun Shin, Kolby Nottingham, Litian Liang, Roy Fox, Sameer Singh","submitted_at":"2021-09-05T20:11:53Z","abstract_excerpt":"Natural language instruction following tasks serve as a valuable test-bed for grounded language and robotics research. However, data collection for these tasks is expensive and end-to-end approaches suffer from data inefficiency. We propose the structuring of language, acting, and visual tasks into separate modules that can be trained independently. Using a Language, Action, and Vision (LAV) framework removes the dependence of action and vision modules on instruction following datasets, making them more efficient to train. We also present a preliminary evaluation of LAV on the ALFRED task for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02161","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/2109.02161/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":"2026-07-05T03:11:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mUUhZc+Wx4yjvOeY7K3ZgfjC8ZLn90N4JUGkHXJhzkoSPVMLQCYuXE62WFXNrt6IdEvSe0Ej7r7XycTMtB7QAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T06:21:03.511154Z"},"content_sha256":"834d6ba5a10c1d0cd9e763f2c62eadcf6957901998da187c5d72d6d93b3c00d9","schema_version":"1.0","event_id":"sha256:834d6ba5a10c1d0cd9e763f2c62eadcf6957901998da187c5d72d6d93b3c00d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/bundle.json","state_url":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/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":"2026-07-18T06:21:03Z","links":{"resolver":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4","bundle":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/bundle.json","state":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MOAOUI5ZPJVSKWATO7LND7YOG4","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":"ba6ccdaaf268d1c68a2653e769068eae3eba58083297b609d9c5d34fd7b5678f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-05T20:11:53Z","title_canon_sha256":"c42e1d1e86cd8507ab6b0e89bf57c9066ea3d838bf61cbb6a69f288e31e3dbc1"},"schema_version":"1.0","source":{"id":"2109.02161","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02161","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02161v1","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02161","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"pith_short_12","alias_value":"MOAOUI5ZPJVS","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"pith_short_16","alias_value":"MOAOUI5ZPJVSKWAT","created_at":"2026-07-05T03:11:39Z"},{"alias_kind":"pith_short_8","alias_value":"MOAOUI5Z","created_at":"2026-07-05T03:11:39Z"}],"graph_snapshots":[{"event_id":"sha256:834d6ba5a10c1d0cd9e763f2c62eadcf6957901998da187c5d72d6d93b3c00d9","target":"graph","created_at":"2026-07-05T03:11:39Z","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/2109.02161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language instruction following tasks serve as a valuable test-bed for grounded language and robotics research. However, data collection for these tasks is expensive and end-to-end approaches suffer from data inefficiency. We propose the structuring of language, acting, and visual tasks into separate modules that can be trained independently. Using a Language, Action, and Vision (LAV) framework removes the dependence of action and vision modules on instruction following datasets, making them more efficient to train. We also present a preliminary evaluation of LAV on the ALFRED task for ","authors_text":"Charless C. Fowlkes, Daeyun Shin, Kolby Nottingham, Litian Liang, Roy Fox, Sameer Singh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-05T20:11:53Z","title":"Modular Framework for Visuomotor Language Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02161","kind":"arxiv","version":1},"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":"sha256:7cb075b9e9c011e51890b8b832690daa62ff58226256bc8fd9ec18aee491f167","target":"record","created_at":"2026-07-05T03:11:39Z","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":"ba6ccdaaf268d1c68a2653e769068eae3eba58083297b609d9c5d34fd7b5678f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-05T20:11:53Z","title_canon_sha256":"c42e1d1e86cd8507ab6b0e89bf57c9066ea3d838bf61cbb6a69f288e31e3dbc1"},"schema_version":"1.0","source":{"id":"2109.02161","kind":"arxiv","version":1}},"canonical_sha256":"6380ea23b97a6b25581377d6d1ff0e3710315593014971535a85b7ae556c53e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6380ea23b97a6b25581377d6d1ff0e3710315593014971535a85b7ae556c53e6","first_computed_at":"2026-07-05T03:11:39.460897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:39.460897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5qlRCuk0r02TIytzDIvxeCQBZImtghaAtdS7sB8d8R7RarS8bkakzPc/ApylTcM4pwWCcE/6qiQjFMnm2sTdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:39.461286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02161","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cb075b9e9c011e51890b8b832690daa62ff58226256bc8fd9ec18aee491f167","sha256:834d6ba5a10c1d0cd9e763f2c62eadcf6957901998da187c5d72d6d93b3c00d9"],"state_sha256":"fc0c336aa571e11d75457a0dabc09f1ff51fab32c1ecabcc6ea50f96e3ea4c0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x2iQCH9y6E/YWPUsrPdgkQHkn9aEOE8rnFQLVUai0JKO/Snyckn/hVMl4DdQ1BzvoeL3tlj32tdeR3Pfogi8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T06:21:03.513231Z","bundle_sha256":"0a5f6d09deae2752cfc33127970be1e2201efff2a7a3648cf06583a665c55583"}}