{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZQX47IVFMPFOMHSKWZAIDYRPCP","short_pith_number":"pith:ZQX47IVF","canonical_record":{"source":{"id":"1704.08795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-28T03:12:57Z","cross_cats_sorted":[],"title_canon_sha256":"8e34a3c7f9fb07066a09b3a6a5df381e64d8d554a8b380a3ab8126950827be8a","abstract_canon_sha256":"47c8849d09eb0d85ad3bd474abeb22858f068445c1b133f2fcc662b42fda2f11"},"schema_version":"1.0"},"canonical_sha256":"cc2fcfa2a563cae61e4ab64081e22f13c05d940334e60571d445e1a69d4bf059","source":{"kind":"arxiv","id":"1704.08795","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08795","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08795v2","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08795","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"ZQX47IVFMPFO","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZQX47IVFMPFOMHSK","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZQX47IVF","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZQX47IVFMPFOMHSKWZAIDYRPCP","target":"record","payload":{"canonical_record":{"source":{"id":"1704.08795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-28T03:12:57Z","cross_cats_sorted":[],"title_canon_sha256":"8e34a3c7f9fb07066a09b3a6a5df381e64d8d554a8b380a3ab8126950827be8a","abstract_canon_sha256":"47c8849d09eb0d85ad3bd474abeb22858f068445c1b133f2fcc662b42fda2f11"},"schema_version":"1.0"},"canonical_sha256":"cc2fcfa2a563cae61e4ab64081e22f13c05d940334e60571d445e1a69d4bf059","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:46.269390Z","signature_b64":"2q3O9vmuHZPGDvLqPPxJ9B2mqJg/04S0JmkoZEudOXi2kRKsypgBmM6wqtcgzXDu5Mk47KqigoC5GYgB+b5HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc2fcfa2a563cae61e4ab64081e22f13c05d940334e60571d445e1a69d4bf059","last_reissued_at":"2026-05-18T00:39:46.268677Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:46.268677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.08795","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":"2026-05-18T00:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8quuSrgXppzvQBOnHtJwHexJxOo5ND5pbwmbHWY3uJaCbfyzmiNi/WfP/HAvyIqp2iwaRhHJc3gJSy3Yn8IVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:33:41.559337Z"},"content_sha256":"73d137426b1168cc54083bbdac37ce98cd4fae16fcc657d75c936c650dd1bb7d","schema_version":"1.0","event_id":"sha256:73d137426b1168cc54083bbdac37ce98cd4fae16fcc657d75c936c650dd1bb7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZQX47IVFMPFOMHSKWZAIDYRPCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipendra Misra, John Langford, Yoav Artzi","submitted_at":"2017-04-28T03:12:57Z","abstract_excerpt":"We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately trained models, we learn a single model to jointly reason about linguistic and visual input. We use reinforcement learning in a contextual bandit setting to train a neural network agent. To guide the agent's exploration, we use reward shaping with different forms of supervision. Our approach does not require intermediate representations, planning procedures, or training different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08795","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":""},"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":"2026-05-18T00:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"khwKKVEKnu5dhhk/0ZCrMx/Zsdnr6U3KwZHkSIUkNda0IabrWLlLbsX0aIcvuKd+QkvQWvFUUVxfCSVMXq0UCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:33:41.560038Z"},"content_sha256":"3db1ba01b58635ada392c0e4fff84d787ee15b28b9bff21c9dd6bfd1fc3ef6a5","schema_version":"1.0","event_id":"sha256:3db1ba01b58635ada392c0e4fff84d787ee15b28b9bff21c9dd6bfd1fc3ef6a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/bundle.json","state_url":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/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":"2026-05-26T21:33:41Z","links":{"resolver":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP","bundle":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/bundle.json","state":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZQX47IVFMPFOMHSKWZAIDYRPCP","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":"47c8849d09eb0d85ad3bd474abeb22858f068445c1b133f2fcc662b42fda2f11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-28T03:12:57Z","title_canon_sha256":"8e34a3c7f9fb07066a09b3a6a5df381e64d8d554a8b380a3ab8126950827be8a"},"schema_version":"1.0","source":{"id":"1704.08795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08795","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08795v2","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08795","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"ZQX47IVFMPFO","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZQX47IVFMPFOMHSK","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZQX47IVF","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:3db1ba01b58635ada392c0e4fff84d787ee15b28b9bff21c9dd6bfd1fc3ef6a5","target":"graph","created_at":"2026-05-18T00:39:46Z","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"},"paper":{"abstract_excerpt":"We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately trained models, we learn a single model to jointly reason about linguistic and visual input. We use reinforcement learning in a contextual bandit setting to train a neural network agent. To guide the agent's exploration, we use reward shaping with different forms of supervision. Our approach does not require intermediate representations, planning procedures, or training different","authors_text":"Dipendra Misra, John Langford, Yoav Artzi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-28T03:12:57Z","title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08795","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":"sha256:73d137426b1168cc54083bbdac37ce98cd4fae16fcc657d75c936c650dd1bb7d","target":"record","created_at":"2026-05-18T00:39:46Z","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":"47c8849d09eb0d85ad3bd474abeb22858f068445c1b133f2fcc662b42fda2f11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-28T03:12:57Z","title_canon_sha256":"8e34a3c7f9fb07066a09b3a6a5df381e64d8d554a8b380a3ab8126950827be8a"},"schema_version":"1.0","source":{"id":"1704.08795","kind":"arxiv","version":2}},"canonical_sha256":"cc2fcfa2a563cae61e4ab64081e22f13c05d940334e60571d445e1a69d4bf059","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc2fcfa2a563cae61e4ab64081e22f13c05d940334e60571d445e1a69d4bf059","first_computed_at":"2026-05-18T00:39:46.268677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:46.268677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2q3O9vmuHZPGDvLqPPxJ9B2mqJg/04S0JmkoZEudOXi2kRKsypgBmM6wqtcgzXDu5Mk47KqigoC5GYgB+b5HCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:46.269390Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.08795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73d137426b1168cc54083bbdac37ce98cd4fae16fcc657d75c936c650dd1bb7d","sha256:3db1ba01b58635ada392c0e4fff84d787ee15b28b9bff21c9dd6bfd1fc3ef6a5"],"state_sha256":"c78b33251609d18e96aa4cbcd69c43ace64a35c82da22cfb007995f89fb3b5ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O56wsyjmVOG7pf/okS319Y8TFVBSevdIBo9Woh2kAb0rqk9TiS5ujpKnL3QNBlsgSp2T3+BfMyFz+QBtCajBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T21:33:41.563678Z","bundle_sha256":"392d617ffb6d6fe5a8dbcd5c4efbae91ad691aa8af2377b224ab0b3a8bf09182"}}