{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZM7QOLYIJEWF5QYM6Q3GAKAHG5","short_pith_number":"pith:ZM7QOLYI","canonical_record":{"source":{"id":"1904.11564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-25T20:01:08Z","cross_cats_sorted":[],"title_canon_sha256":"6f2821fb905a36e32b6c203c450e4fff18637c2057db43f6a46085dca853f498","abstract_canon_sha256":"940b2b2c34de8238d78bdbad1f41788427b593c569933bff264e22c3f03057f2"},"schema_version":"1.0"},"canonical_sha256":"cb3f072f08492c5ec30cf43660280737747d145c5b2cf9bce3580ddf08a85901","source":{"kind":"arxiv","id":"1904.11564","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11564","created_at":"2026-05-17T23:47:43Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11564v1","created_at":"2026-05-17T23:47:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11564","created_at":"2026-05-17T23:47:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZM7QOLYIJEWF","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZM7QOLYIJEWF5QYM","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZM7QOLYI","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZM7QOLYIJEWF5QYM6Q3GAKAHG5","target":"record","payload":{"canonical_record":{"source":{"id":"1904.11564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-25T20:01:08Z","cross_cats_sorted":[],"title_canon_sha256":"6f2821fb905a36e32b6c203c450e4fff18637c2057db43f6a46085dca853f498","abstract_canon_sha256":"940b2b2c34de8238d78bdbad1f41788427b593c569933bff264e22c3f03057f2"},"schema_version":"1.0"},"canonical_sha256":"cb3f072f08492c5ec30cf43660280737747d145c5b2cf9bce3580ddf08a85901","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:43.371192Z","signature_b64":"8iblDqYfbbtbpBvEfYgNS5xPkSY4t4aL7cbEJM/1R5aW2HS82lwuLGJGRRJNobh7BaNIzyZLOgcbg3dtck9gCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb3f072f08492c5ec30cf43660280737747d145c5b2cf9bce3580ddf08a85901","last_reissued_at":"2026-05-17T23:47:43.370697Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:43.370697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.11564","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":"2026-05-17T23:47:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EmcgY0dFl8UcoCWVfha05PpugEnO9myqqAYzlNuO/3aSPAReryyKsmPnMShS08bnVoVDqzYL1Dl+f2YmHKE1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:25:57.145381Z"},"content_sha256":"9db638c8a64867e5814c085336274cbde5bb21f4364b99f55f70c3011a28bf75","schema_version":"1.0","event_id":"sha256:9db638c8a64867e5814c085336274cbde5bb21f4364b99f55f70c3011a28bf75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZM7QOLYIJEWF5QYM6Q3GAKAHG5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Text Generation from Rich Semantic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emily M. Bender, Jan Buys, Michael W. Goodman, Valerie Hajdik","submitted_at":"2019-04-25T20:01:08Z","abstract_excerpt":"We propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS). MRS is a rich semantic representation that encodes more precise semantic detail than other representations such as Abstract Meaning Representation (AMR). We show that a sequence-to-sequence model that maps a linearization of Dependency MRS, a graph-based representation of MRS, to English text can achieve a BLEU score of 66.11 when trained on gold data. The performance can be improved further using a high-precision, broad coverage grammar-based parser to generate a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11564","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":""},"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":"2026-05-17T23:47:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ouNyewrpi8F6U5UK4Qm3V07EIn89cNF0z7DpiJffJvzdbqNI9bRnX1OCWgMrmyke7c7q3uBbQt9VkcQWhvK0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:25:57.145751Z"},"content_sha256":"836d3720e9f910476fbab7f821d1844b1539021d3f1d717b48d5e92d6810bfcb","schema_version":"1.0","event_id":"sha256:836d3720e9f910476fbab7f821d1844b1539021d3f1d717b48d5e92d6810bfcb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZM7QOLYIJEWF5QYM6Q3GAKAHG5/bundle.json","state_url":"https://pith.science/pith/ZM7QOLYIJEWF5QYM6Q3GAKAHG5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZM7QOLYIJEWF5QYM6Q3GAKAHG5/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":"2026-06-06T19:25:57Z","links":{"resolver":"https://pith.science/pith/ZM7QOLYIJEWF5QYM6Q3GAKAHG5","bundle":"https://pith.science/pith/ZM7QOLYIJEWF5QYM6Q3GAKAHG5/bundle.json","state":"https://pith.science/pith/ZM7QOLYIJEWF5QYM6Q3GAKAHG5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZM7QOLYIJEWF5QYM6Q3GAKAHG5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZM7QOLYIJEWF5QYM6Q3GAKAHG5","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":"940b2b2c34de8238d78bdbad1f41788427b593c569933bff264e22c3f03057f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-25T20:01:08Z","title_canon_sha256":"6f2821fb905a36e32b6c203c450e4fff18637c2057db43f6a46085dca853f498"},"schema_version":"1.0","source":{"id":"1904.11564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11564","created_at":"2026-05-17T23:47:43Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11564v1","created_at":"2026-05-17T23:47:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11564","created_at":"2026-05-17T23:47:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZM7QOLYIJEWF","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZM7QOLYIJEWF5QYM","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZM7QOLYI","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:836d3720e9f910476fbab7f821d1844b1539021d3f1d717b48d5e92d6810bfcb","target":"graph","created_at":"2026-05-17T23:47:43Z","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 neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS). MRS is a rich semantic representation that encodes more precise semantic detail than other representations such as Abstract Meaning Representation (AMR). We show that a sequence-to-sequence model that maps a linearization of Dependency MRS, a graph-based representation of MRS, to English text can achieve a BLEU score of 66.11 when trained on gold data. The performance can be improved further using a high-precision, broad coverage grammar-based parser to generate a ","authors_text":"Emily M. Bender, Jan Buys, Michael W. Goodman, Valerie Hajdik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-25T20:01:08Z","title":"Neural Text Generation from Rich Semantic Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11564","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":"sha256:9db638c8a64867e5814c085336274cbde5bb21f4364b99f55f70c3011a28bf75","target":"record","created_at":"2026-05-17T23:47:43Z","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":"940b2b2c34de8238d78bdbad1f41788427b593c569933bff264e22c3f03057f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-25T20:01:08Z","title_canon_sha256":"6f2821fb905a36e32b6c203c450e4fff18637c2057db43f6a46085dca853f498"},"schema_version":"1.0","source":{"id":"1904.11564","kind":"arxiv","version":1}},"canonical_sha256":"cb3f072f08492c5ec30cf43660280737747d145c5b2cf9bce3580ddf08a85901","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb3f072f08492c5ec30cf43660280737747d145c5b2cf9bce3580ddf08a85901","first_computed_at":"2026-05-17T23:47:43.370697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:43.370697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8iblDqYfbbtbpBvEfYgNS5xPkSY4t4aL7cbEJM/1R5aW2HS82lwuLGJGRRJNobh7BaNIzyZLOgcbg3dtck9gCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:43.371192Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9db638c8a64867e5814c085336274cbde5bb21f4364b99f55f70c3011a28bf75","sha256:836d3720e9f910476fbab7f821d1844b1539021d3f1d717b48d5e92d6810bfcb"],"state_sha256":"54a7aef8529dc19013f971980486b52b3520ed66a6da1926f1ae1572f2888fd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1sPCxfzrYs/FwkZJ7KE+Nq1SZOklzrUanJkYl73O8BAIZZF8hTfcgp/9NYsRM67YgcxvyDsZPRSNO74Xj6esDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:25:57.147745Z","bundle_sha256":"005e693fd210c7ef1950fe48bf1c553719cbd7a16a8b3bb347770545e1332ca4"}}