{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y57G3HCEI66S5HESBHJVVB4WG4","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":"0725453d9ac97daafe15c9133ef880f1c3c1ed07e0f89b36a49687cfefbade3f","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T18:58:42Z","title_canon_sha256":"3d2994c142f454e435f055574454c356fa4faf63b7a922d0eab022c44233e489"},"schema_version":"1.0","source":{"id":"1811.07882","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07882","created_at":"2026-05-17T23:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07882v2","created_at":"2026-05-17T23:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07882","created_at":"2026-05-17T23:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"Y57G3HCEI66S","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y57G3HCEI66S5HES","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y57G3HCE","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:e71bbd6c2a1d5b60c9da99a2622adff2af29e2f4b93e56cb191b43f883f46576","target":"graph","created_at":"2026-05-17T23:55:19Z","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":"Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their disadvantages: reward functions require manual engineering, while demonstrations require a human expert to be able to actually perform the task in order to generate the demonstration. Instruction following from natural language instructions provides an appealing alternative: in the same way that we can specify goals to other humans simply by speaking or writing, we w","authors_text":"Abhishek Gupta, Jacob Andreas, John D. Co-Reyes, John DeNero, Nick Altieri, Pieter Abbeel, Sergey Levine, Suvansh Sanjeev","cross_cats":["cs.AI","cs.CL","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T18:58:42Z","title":"Guiding Policies with Language via Meta-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07882","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":"sha256:6a8216e8fe9b15a3a0cfe20d5c2e214ccfd0d29aa95fa0a64e5b97b279078e98","target":"record","created_at":"2026-05-17T23:55:19Z","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":"0725453d9ac97daafe15c9133ef880f1c3c1ed07e0f89b36a49687cfefbade3f","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T18:58:42Z","title_canon_sha256":"3d2994c142f454e435f055574454c356fa4faf63b7a922d0eab022c44233e489"},"schema_version":"1.0","source":{"id":"1811.07882","kind":"arxiv","version":2}},"canonical_sha256":"c77e6d9c4447bd2e9c9209d35a87963717d7304d7ba8c596385ec46c9302491e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c77e6d9c4447bd2e9c9209d35a87963717d7304d7ba8c596385ec46c9302491e","first_computed_at":"2026-05-17T23:55:19.090685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:19.090685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A8m5xB8qm9eRXakHlMqi4X0wtApaJdv3RqEdNlPbhPATw4O4k86pBk1y3fjs8InM5z5wVITswY5om7CMS/aeAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:19.091118Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.07882","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a8216e8fe9b15a3a0cfe20d5c2e214ccfd0d29aa95fa0a64e5b97b279078e98","sha256:e71bbd6c2a1d5b60c9da99a2622adff2af29e2f4b93e56cb191b43f883f46576"],"state_sha256":"8293c2be6993378cd5cf136e353cec5c7fb428ab7c401edabf77ef6fdf3ddd05"}