{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:X56CC3OM2S4AOQSBBB3T2KCNKI","short_pith_number":"pith:X56CC3OM","canonical_record":{"source":{"id":"1811.01090","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T21:14:46Z","cross_cats_sorted":[],"title_canon_sha256":"8c117324f07d6175a23aa0e2754ca08d70a485723a5f88e64b808d2253316b71","abstract_canon_sha256":"87e7b133bf49e69f43fb73db6dd47f48bada1bf7d463769c58da70762218a583"},"schema_version":"1.0"},"canonical_sha256":"bf7c216dccd4b807424108773d284d523d355945960ce48ced853b9719725aa9","source":{"kind":"arxiv","id":"1811.01090","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01090","created_at":"2026-05-17T23:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01090v2","created_at":"2026-05-17T23:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01090","created_at":"2026-05-17T23:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"X56CC3OM2S4A","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"X56CC3OM2S4AOQSB","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"X56CC3OM","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:X56CC3OM2S4AOQSBBB3T2KCNKI","target":"record","payload":{"canonical_record":{"source":{"id":"1811.01090","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T21:14:46Z","cross_cats_sorted":[],"title_canon_sha256":"8c117324f07d6175a23aa0e2754ca08d70a485723a5f88e64b808d2253316b71","abstract_canon_sha256":"87e7b133bf49e69f43fb73db6dd47f48bada1bf7d463769c58da70762218a583"},"schema_version":"1.0"},"canonical_sha256":"bf7c216dccd4b807424108773d284d523d355945960ce48ced853b9719725aa9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:50.460007Z","signature_b64":"6vZjsBR3l5Egmb3CgAalKQif0oBqNywXfFnCndxEzpvNVp/IhkCdPYAtPjVSuwo3Ra7w3JZuiTxH112p0QhvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf7c216dccd4b807424108773d284d523d355945960ce48ced853b9719725aa9","last_reissued_at":"2026-05-17T23:50:50.459490Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:50.459490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.01090","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":"2026-05-17T23:50:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f5vwAkVJ+1qPKQxAM/Coz5WqrocEs0Lbdk01zKQzpxFf1UnBLQ0p2UC5fF7nr4RVCUJ8Qc3b+YGSxqe+9yhqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T18:18:49.628307Z"},"content_sha256":"dbac3fd1cac0fe2371cd278e66cfd4cff22cda10b905f5a29b429427d6720900","schema_version":"1.0","event_id":"sha256:dbac3fd1cac0fe2371cd278e66cfd4cff22cda10b905f5a29b429427d6720900"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:X56CC3OM2S4AOQSBBB3T2KCNKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Value-based Search in Execution Space for Mapping Instructions to Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dor Muhlgay, Jonathan Berant, Jonathan Herzig","submitted_at":"2018-11-02T21:14:46Z","abstract_excerpt":"Training models to map natural language instructions to programs given target world supervision only requires searching for good programs at training time. Search is commonly done using beam search in the space of partial programs or program trees, but as the length of the instructions grows finding a good program becomes difficult. In this work, we propose a search algorithm that uses the target world state, known at training time, to train a critic network that predicts the expected reward of every search state. We then score search states on the beam by interpolating their expected reward w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01090","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":"2026-05-17T23:50:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hDBOUKa8CNG5SZQRKYXgr4TfuaENmnVRGqlviAnrlIx7Hr8GyU0G7cY0oeXsFd3U4IIXdG3BU4nbI8RO9A5rAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T18:18:49.628964Z"},"content_sha256":"06dc29381b7859219e616721d6a72a017aeb7c1ad9f3c71ef976b9a7e139e63d","schema_version":"1.0","event_id":"sha256:06dc29381b7859219e616721d6a72a017aeb7c1ad9f3c71ef976b9a7e139e63d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X56CC3OM2S4AOQSBBB3T2KCNKI/bundle.json","state_url":"https://pith.science/pith/X56CC3OM2S4AOQSBBB3T2KCNKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X56CC3OM2S4AOQSBBB3T2KCNKI/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":"2026-05-24T18:18:49Z","links":{"resolver":"https://pith.science/pith/X56CC3OM2S4AOQSBBB3T2KCNKI","bundle":"https://pith.science/pith/X56CC3OM2S4AOQSBBB3T2KCNKI/bundle.json","state":"https://pith.science/pith/X56CC3OM2S4AOQSBBB3T2KCNKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X56CC3OM2S4AOQSBBB3T2KCNKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:X56CC3OM2S4AOQSBBB3T2KCNKI","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":"87e7b133bf49e69f43fb73db6dd47f48bada1bf7d463769c58da70762218a583","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T21:14:46Z","title_canon_sha256":"8c117324f07d6175a23aa0e2754ca08d70a485723a5f88e64b808d2253316b71"},"schema_version":"1.0","source":{"id":"1811.01090","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01090","created_at":"2026-05-17T23:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01090v2","created_at":"2026-05-17T23:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01090","created_at":"2026-05-17T23:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"X56CC3OM2S4A","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"X56CC3OM2S4AOQSB","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"X56CC3OM","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:06dc29381b7859219e616721d6a72a017aeb7c1ad9f3c71ef976b9a7e139e63d","target":"graph","created_at":"2026-05-17T23:50:50Z","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":"Training models to map natural language instructions to programs given target world supervision only requires searching for good programs at training time. Search is commonly done using beam search in the space of partial programs or program trees, but as the length of the instructions grows finding a good program becomes difficult. In this work, we propose a search algorithm that uses the target world state, known at training time, to train a critic network that predicts the expected reward of every search state. We then score search states on the beam by interpolating their expected reward w","authors_text":"Dor Muhlgay, Jonathan Berant, Jonathan Herzig","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T21:14:46Z","title":"Value-based Search in Execution Space for Mapping Instructions to Programs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01090","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:dbac3fd1cac0fe2371cd278e66cfd4cff22cda10b905f5a29b429427d6720900","target":"record","created_at":"2026-05-17T23:50:50Z","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":"87e7b133bf49e69f43fb73db6dd47f48bada1bf7d463769c58da70762218a583","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T21:14:46Z","title_canon_sha256":"8c117324f07d6175a23aa0e2754ca08d70a485723a5f88e64b808d2253316b71"},"schema_version":"1.0","source":{"id":"1811.01090","kind":"arxiv","version":2}},"canonical_sha256":"bf7c216dccd4b807424108773d284d523d355945960ce48ced853b9719725aa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf7c216dccd4b807424108773d284d523d355945960ce48ced853b9719725aa9","first_computed_at":"2026-05-17T23:50:50.459490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:50.459490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6vZjsBR3l5Egmb3CgAalKQif0oBqNywXfFnCndxEzpvNVp/IhkCdPYAtPjVSuwo3Ra7w3JZuiTxH112p0QhvBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:50.460007Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.01090","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbac3fd1cac0fe2371cd278e66cfd4cff22cda10b905f5a29b429427d6720900","sha256:06dc29381b7859219e616721d6a72a017aeb7c1ad9f3c71ef976b9a7e139e63d"],"state_sha256":"38073a7b7518fac04fd01779d99f93b0278a9e0338c3a0f6cabf6d83b974fd09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PxyPhDMaa0dVB+eShze59m27iNvpknY0UvF8Rgl6A9aKHHD5ek4QCgdqdbl1+9EE2uQOrDRdrdCOhIPzAz8WBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T18:18:49.632326Z","bundle_sha256":"e344cc03f641fe2f5357356b6391cd2509b023d1529daa9b26a7f7c06c1613dd"}}