{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:O73JXBXEHWWOUOT3U4AM62SKF4","short_pith_number":"pith:O73JXBXE","canonical_record":{"source":{"id":"1911.02808","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T08:58:02Z","cross_cats_sorted":[],"title_canon_sha256":"067f809c19d8c32b33e019b79eab6bb9cc889675cc2e548e0fdb59306bd17310","abstract_canon_sha256":"5c90a1d22dd2412fe6616da4b4ba192c7eecb2d11be6e169d04216f787fef06b"},"schema_version":"1.0"},"canonical_sha256":"77f69b86e43dacea3a7ba700cf6a4a2f0cce1d67a0a151f6bbb0ee80022176ea","source":{"kind":"arxiv","id":"1911.02808","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02808","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02808v1","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02808","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"O73JXBXEHWWO","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"O73JXBXEHWWOUOT3","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"O73JXBXE","created_at":"2026-07-05T00:17:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:O73JXBXEHWWOUOT3U4AM62SKF4","target":"record","payload":{"canonical_record":{"source":{"id":"1911.02808","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T08:58:02Z","cross_cats_sorted":[],"title_canon_sha256":"067f809c19d8c32b33e019b79eab6bb9cc889675cc2e548e0fdb59306bd17310","abstract_canon_sha256":"5c90a1d22dd2412fe6616da4b4ba192c7eecb2d11be6e169d04216f787fef06b"},"schema_version":"1.0"},"canonical_sha256":"77f69b86e43dacea3a7ba700cf6a4a2f0cce1d67a0a151f6bbb0ee80022176ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:57.019686Z","signature_b64":"kWIb+TJYDs1+IylHmswKA8btBzlzjGZwkiut5i0b7gY83wuFvnof7ionyo5PQpAtjAyxxBuvfmGczRj7TQHQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77f69b86e43dacea3a7ba700cf6a4a2f0cce1d67a0a151f6bbb0ee80022176ea","last_reissued_at":"2026-07-05T00:17:57.019291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:57.019291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.02808","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":"2026-07-05T00:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lPCdoFgCBjD3Fia7uv+2YwZVXV9BQJCxeKZ89wfqeILWEdkBFOix+2O+Fb71kZjEQk8lzZbD7Jztz2eAhJ2nAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:31:31.341648Z"},"content_sha256":"fe12bfcc87807e346f76cdb05815c37ef268bb04a90e081758aa61568e5c75de","schema_version":"1.0","event_id":"sha256:fe12bfcc87807e346f76cdb05815c37ef268bb04a90e081758aa61568e5c75de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:O73JXBXEHWWOUOT3U4AM62SKF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transition-Based Deep Input Linearization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Manish Shrivastava, Ratish Puduppully, Yue Zhang","submitted_at":"2019-11-07T08:58:02Z","abstract_excerpt":"Traditional methods for deep NLG adopt pipeline approaches comprising stages such as constructing syntactic input, predicting function words, linearizing the syntactic input and generating the surface forms. Though easier to visualize, pipeline approaches suffer from error propagation. In addition, information available across modules cannot be leveraged by all modules. We construct a transition-based model to jointly perform linearization, function word prediction and morphological generation, which considerably improves upon the accuracy compared to a pipelined baseline system. On a standard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02808","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.02808/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vQxc09Z0WsC3R6Z6bsy9zAMyIorE8gqco1vptkW4IQ+iTkZMGK3JR1aQ8xqKpLVi1giXkapRtzgP+oeKsxl4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:31:31.342176Z"},"content_sha256":"37cc15a5375ca15cb7f3d5a53dfa51d47df3ed93a0e5e4e2f0128e52b881430f","schema_version":"1.0","event_id":"sha256:37cc15a5375ca15cb7f3d5a53dfa51d47df3ed93a0e5e4e2f0128e52b881430f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O73JXBXEHWWOUOT3U4AM62SKF4/bundle.json","state_url":"https://pith.science/pith/O73JXBXEHWWOUOT3U4AM62SKF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O73JXBXEHWWOUOT3U4AM62SKF4/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":"2026-08-03T17:31:31Z","links":{"resolver":"https://pith.science/pith/O73JXBXEHWWOUOT3U4AM62SKF4","bundle":"https://pith.science/pith/O73JXBXEHWWOUOT3U4AM62SKF4/bundle.json","state":"https://pith.science/pith/O73JXBXEHWWOUOT3U4AM62SKF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O73JXBXEHWWOUOT3U4AM62SKF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:O73JXBXEHWWOUOT3U4AM62SKF4","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":"5c90a1d22dd2412fe6616da4b4ba192c7eecb2d11be6e169d04216f787fef06b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T08:58:02Z","title_canon_sha256":"067f809c19d8c32b33e019b79eab6bb9cc889675cc2e548e0fdb59306bd17310"},"schema_version":"1.0","source":{"id":"1911.02808","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02808","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02808v1","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02808","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"O73JXBXEHWWO","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"O73JXBXEHWWOUOT3","created_at":"2026-07-05T00:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"O73JXBXE","created_at":"2026-07-05T00:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:37cc15a5375ca15cb7f3d5a53dfa51d47df3ed93a0e5e4e2f0128e52b881430f","target":"graph","created_at":"2026-07-05T00:17:57Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.02808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional methods for deep NLG adopt pipeline approaches comprising stages such as constructing syntactic input, predicting function words, linearizing the syntactic input and generating the surface forms. Though easier to visualize, pipeline approaches suffer from error propagation. In addition, information available across modules cannot be leveraged by all modules. We construct a transition-based model to jointly perform linearization, function word prediction and morphological generation, which considerably improves upon the accuracy compared to a pipelined baseline system. On a standard","authors_text":"Manish Shrivastava, Ratish Puduppully, Yue Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T08:58:02Z","title":"Transition-Based Deep Input Linearization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02808","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:fe12bfcc87807e346f76cdb05815c37ef268bb04a90e081758aa61568e5c75de","target":"record","created_at":"2026-07-05T00:17:57Z","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":"5c90a1d22dd2412fe6616da4b4ba192c7eecb2d11be6e169d04216f787fef06b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T08:58:02Z","title_canon_sha256":"067f809c19d8c32b33e019b79eab6bb9cc889675cc2e548e0fdb59306bd17310"},"schema_version":"1.0","source":{"id":"1911.02808","kind":"arxiv","version":1}},"canonical_sha256":"77f69b86e43dacea3a7ba700cf6a4a2f0cce1d67a0a151f6bbb0ee80022176ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77f69b86e43dacea3a7ba700cf6a4a2f0cce1d67a0a151f6bbb0ee80022176ea","first_computed_at":"2026-07-05T00:17:57.019291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:17:57.019291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kWIb+TJYDs1+IylHmswKA8btBzlzjGZwkiut5i0b7gY83wuFvnof7ionyo5PQpAtjAyxxBuvfmGczRj7TQHQCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:17:57.019686Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.02808","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe12bfcc87807e346f76cdb05815c37ef268bb04a90e081758aa61568e5c75de","sha256:37cc15a5375ca15cb7f3d5a53dfa51d47df3ed93a0e5e4e2f0128e52b881430f"],"state_sha256":"67afcec0a6ce5c12ca25b856a8f807e6128f322d10c2c6e54eb3a139684eadcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2h/67XxttiKt5pPkVzXfAgOLeX/VVvDKgnMkSY7deyZOBFjkbX79AaT6sDQCPTQXl4Ucm+bCDJKvvSiEeYLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:31:31.347272Z","bundle_sha256":"da3ab33acd5a73d74beee0cd6b8675e2e9118b5fb713afae6009fbaf0188d85f"}}