{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XEL7765RSNUCAAIVYLU2W34K4D","short_pith_number":"pith:XEL7765R","canonical_record":{"source":{"id":"1911.06156","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T04:42:13Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"54ee5b8cebcf7be86d8355f8227e76550bd83aca65ce8f8b7e7b07517bc96140","abstract_canon_sha256":"0f15cf73982963637c8703e6c3947855f417ec7fdb6e0390bdbbca3100c04824"},"schema_version":"1.0"},"canonical_sha256":"b917fffbb19368200115c2e9ab6f8ae0ce68b77a4fbe88ec3b30af26019cae04","source":{"kind":"arxiv","id":"1911.06156","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06156","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06156v1","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06156","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"XEL7765RSNUC","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"XEL7765RSNUCAAIV","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"XEL7765R","created_at":"2026-07-05T00:19:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XEL7765RSNUCAAIVYLU2W34K4D","target":"record","payload":{"canonical_record":{"source":{"id":"1911.06156","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T04:42:13Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"54ee5b8cebcf7be86d8355f8227e76550bd83aca65ce8f8b7e7b07517bc96140","abstract_canon_sha256":"0f15cf73982963637c8703e6c3947855f417ec7fdb6e0390bdbbca3100c04824"},"schema_version":"1.0"},"canonical_sha256":"b917fffbb19368200115c2e9ab6f8ae0ce68b77a4fbe88ec3b30af26019cae04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:15.684506Z","signature_b64":"cRPYoHg3kBjTJqGWQ5GiuTHm+/Bu7zMTpuag6cisZABGbBl/77SFiQ9rc3OVYwptMkEEMvpLqN+BPFrDY9ATAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b917fffbb19368200115c2e9ab6f8ae0ce68b77a4fbe88ec3b30af26019cae04","last_reissued_at":"2026-07-05T00:19:15.684121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:15.684121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.06156","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":"2026-07-05T00:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tmDeDmu4qfqAWRl0GNqTAMlhkve0Q7z91Fz9+JsbSLtK7GNfpD9/drxBiJFnMoZe3S0zdPaMNkDJjZkMoNa2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:12:53.260826Z"},"content_sha256":"ef4b90eb05abf0b71ae84ba325cd7d277329d6978c0a28db2fe20125e7004d85","schema_version":"1.0","event_id":"sha256:ef4b90eb05abf0b71ae84ba325cd7d277329d6978c0a28db2fe20125e7004d85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XEL7765RSNUCAAIVYLU2W34K4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Dhanasekar Sundararaman, Dinghan Shen, Dong Wang, Guoyin Wang, Lawrence Carin, Shijing Si, Vivek Subramanian","submitted_at":"2019-11-10T04:42:13Z","abstract_excerpt":"Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates abstract representations of tokens inputted to an encoder based on their relationships to all tokens in a sequence. Recent studies have shown that although such models are capable of learning syntactic features purely by seeing examples, explicitly feeding this information to deep learning models can significantly enhance their performance. Leveraging syntactic information like part of speech (POS) may be particular"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06156","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/1911.06156/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":"2026-07-05T00:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5jSaFUyoSWBceI04fOVa6lFZ+vl8Xhr80yfsbm5sTw1YdBAlf7zWu7b+oEaTgljVVXdtCNW+MmDwI8po7chAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:12:53.261495Z"},"content_sha256":"8e0f1e8f02713202a7123bd6029ca2ec17d07fa94599eee5114722aba512eb70","schema_version":"1.0","event_id":"sha256:8e0f1e8f02713202a7123bd6029ca2ec17d07fa94599eee5114722aba512eb70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XEL7765RSNUCAAIVYLU2W34K4D/bundle.json","state_url":"https://pith.science/pith/XEL7765RSNUCAAIVYLU2W34K4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XEL7765RSNUCAAIVYLU2W34K4D/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":"2026-07-09T07:12:53Z","links":{"resolver":"https://pith.science/pith/XEL7765RSNUCAAIVYLU2W34K4D","bundle":"https://pith.science/pith/XEL7765RSNUCAAIVYLU2W34K4D/bundle.json","state":"https://pith.science/pith/XEL7765RSNUCAAIVYLU2W34K4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XEL7765RSNUCAAIVYLU2W34K4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XEL7765RSNUCAAIVYLU2W34K4D","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":"0f15cf73982963637c8703e6c3947855f417ec7fdb6e0390bdbbca3100c04824","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T04:42:13Z","title_canon_sha256":"54ee5b8cebcf7be86d8355f8227e76550bd83aca65ce8f8b7e7b07517bc96140"},"schema_version":"1.0","source":{"id":"1911.06156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06156","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06156v1","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06156","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"XEL7765RSNUC","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"XEL7765RSNUCAAIV","created_at":"2026-07-05T00:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"XEL7765R","created_at":"2026-07-05T00:19:15Z"}],"graph_snapshots":[{"event_id":"sha256:8e0f1e8f02713202a7123bd6029ca2ec17d07fa94599eee5114722aba512eb70","target":"graph","created_at":"2026-07-05T00:19:15Z","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/1911.06156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates abstract representations of tokens inputted to an encoder based on their relationships to all tokens in a sequence. Recent studies have shown that although such models are capable of learning syntactic features purely by seeing examples, explicitly feeding this information to deep learning models can significantly enhance their performance. Leveraging syntactic information like part of speech (POS) may be particular","authors_text":"Dhanasekar Sundararaman, Dinghan Shen, Dong Wang, Guoyin Wang, Lawrence Carin, Shijing Si, Vivek Subramanian","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T04:42:13Z","title":"Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06156","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:ef4b90eb05abf0b71ae84ba325cd7d277329d6978c0a28db2fe20125e7004d85","target":"record","created_at":"2026-07-05T00:19:15Z","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":"0f15cf73982963637c8703e6c3947855f417ec7fdb6e0390bdbbca3100c04824","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T04:42:13Z","title_canon_sha256":"54ee5b8cebcf7be86d8355f8227e76550bd83aca65ce8f8b7e7b07517bc96140"},"schema_version":"1.0","source":{"id":"1911.06156","kind":"arxiv","version":1}},"canonical_sha256":"b917fffbb19368200115c2e9ab6f8ae0ce68b77a4fbe88ec3b30af26019cae04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b917fffbb19368200115c2e9ab6f8ae0ce68b77a4fbe88ec3b30af26019cae04","first_computed_at":"2026-07-05T00:19:15.684121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:19:15.684121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cRPYoHg3kBjTJqGWQ5GiuTHm+/Bu7zMTpuag6cisZABGbBl/77SFiQ9rc3OVYwptMkEEMvpLqN+BPFrDY9ATAw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:19:15.684506Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.06156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef4b90eb05abf0b71ae84ba325cd7d277329d6978c0a28db2fe20125e7004d85","sha256:8e0f1e8f02713202a7123bd6029ca2ec17d07fa94599eee5114722aba512eb70"],"state_sha256":"d452e5a30fc6e6fd6b92e1163cc082f2f93362851283f67c068ca573b50a8004"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yth+OlWgU2JvpMxadjGM4iybJpPhZO0TSCDVMd6/JwvTi2a9OxP2bwkzycnBRM3NJZUEoW8O6he80/nZu1gaBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T07:12:53.265588Z","bundle_sha256":"ddfefd8a81379beab3ad4781aca15fd142ed215db617bd3f349285eeff342f75"}}