{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:G3QTPYGP3YN4DSPZVFKDIHYT3K","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":"73ca4a3b677c0248cb89ee4e2f81448f4a8f57a2fb14a339bac1b286437d6886","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T15:47:38Z","title_canon_sha256":"c1e3e3950b3d3a27a187081adc1ee0564d3a87afa081858c5f28e1fb17c6451b"},"schema_version":"1.0","source":{"id":"1805.10209","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10209","created_at":"2026-05-18T00:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10209v2","created_at":"2026-05-18T00:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10209","created_at":"2026-05-18T00:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"G3QTPYGP3YN4","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G3QTPYGP3YN4DSPZ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G3QTPYGP","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:507bdf0098a71027bccd07b76eb1f1df62d2225059113c2dff366976496218bc","target":"graph","created_at":"2026-05-18T00:13:44Z","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 a learning approach for mapping context-dependent sequential instructions to actions. We address the problem of discourse and state dependencies with an attention-based model that considers both the history of the interaction and the state of the world. To train from start and goal states without access to demonstrations, we propose SESTRA, a learning algorithm that takes advantage of single-step reward observations and immediate expected reward maximization. We evaluate on the SCONE domains, and show absolute accuracy improvements of 9.8%-25.3% across the domains over approaches th","authors_text":"Alane Suhr, Yoav Artzi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T15:47:38Z","title":"Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10209","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":"sha256:7b00c3e68a7100fa24f24e7e8262f7aa1b000d44bf3c5d0a64578b27ac5e494e","target":"record","created_at":"2026-05-18T00:13:44Z","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":"73ca4a3b677c0248cb89ee4e2f81448f4a8f57a2fb14a339bac1b286437d6886","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T15:47:38Z","title_canon_sha256":"c1e3e3950b3d3a27a187081adc1ee0564d3a87afa081858c5f28e1fb17c6451b"},"schema_version":"1.0","source":{"id":"1805.10209","kind":"arxiv","version":2}},"canonical_sha256":"36e137e0cfde1bc1c9f9a954341f13da9502be30db45be32dd6ab1962da8c48a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36e137e0cfde1bc1c9f9a954341f13da9502be30db45be32dd6ab1962da8c48a","first_computed_at":"2026-05-18T00:13:44.163985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:44.163985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IAH5sThbbPnMDJI+rYK6SvjW8ZJFsGfpU9NrZ0lB12vhbu3KjsSJvBYji/6liQOTdA9nl39XmX5nKogjySNLDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:44.164720Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.10209","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b00c3e68a7100fa24f24e7e8262f7aa1b000d44bf3c5d0a64578b27ac5e494e","sha256:507bdf0098a71027bccd07b76eb1f1df62d2225059113c2dff366976496218bc"],"state_sha256":"8a513f22f80a0717b21795d2e0d7bb4cfa4b34d2050878e0fe352732caeb7781"}