{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:P2EZV3TOZON5MSIAD4SPQATOZS","short_pith_number":"pith:P2EZV3TO","canonical_record":{"source":{"id":"1611.06639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-21T03:26:29Z","cross_cats_sorted":[],"title_canon_sha256":"a7cefdb22c8474a7c886364b54f834d92dd94b239084074a3f4e967944472e63","abstract_canon_sha256":"f0d3493965af10de6642c808c9ac631d002b268341cd496a174c60d16bf76a16"},"schema_version":"1.0"},"canonical_sha256":"7e899aee6ecb9bd649001f24f8026eccad0be3fc2d1dfc0ada1a4530c14381c2","source":{"kind":"arxiv","id":"1611.06639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06639","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06639v1","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06639","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"pith_short_12","alias_value":"P2EZV3TOZON5","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"P2EZV3TOZON5MSIA","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"P2EZV3TO","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:P2EZV3TOZON5MSIAD4SPQATOZS","target":"record","payload":{"canonical_record":{"source":{"id":"1611.06639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-21T03:26:29Z","cross_cats_sorted":[],"title_canon_sha256":"a7cefdb22c8474a7c886364b54f834d92dd94b239084074a3f4e967944472e63","abstract_canon_sha256":"f0d3493965af10de6642c808c9ac631d002b268341cd496a174c60d16bf76a16"},"schema_version":"1.0"},"canonical_sha256":"7e899aee6ecb9bd649001f24f8026eccad0be3fc2d1dfc0ada1a4530c14381c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:33.305966Z","signature_b64":"sXaJVWTwAs6Kl2WEkka/LuPu/a/HrnQdzBd0A/hJ7Bs132bsKmot7wuwR2xKln8laV5ArOJbC/mGjyLQqWEJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e899aee6ecb9bd649001f24f8026eccad0be3fc2d1dfc0ada1a4530c14381c2","last_reissued_at":"2026-05-18T00:57:33.305406Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:33.305406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.06639","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":"2026-05-18T00:57:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7HMQH8kncRx4tCt3Ch2UJwS3ppS51syfREqTNWt1kOpK9gmkob2vGaXVN+Z+p+UXvf7DHUxGQWrGBmbLyNVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:22:36.508066Z"},"content_sha256":"6e14ec8452f8a1c4168e3f960cf7e713ad14631f3046bb2cec5c07fae22de78c","schema_version":"1.0","event_id":"sha256:6e14ec8452f8a1c4168e3f960cf7e713ad14631f3046bb2cec5c07fae22de78c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:P2EZV3TOZON5MSIAD4SPQATOZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Xu, Hongyun Bao, Jiaming Xu, Peng Zhou, Suncong Zheng, Zhenyu Qi","submitted_at":"2016-11-21T03:26:29Z","abstract_excerpt":"Recurrent Neural Network (RNN) is one of the most popular architectures used in Natural Language Processsing (NLP) tasks because its recurrent structure is very suitable to process variable-length text. RNN can utilize distributed representations of words by first converting the tokens comprising each text into vectors, which form a matrix. And this matrix includes two dimensions: the time-step dimension and the feature vector dimension. Then most existing models usually utilize one-dimensional (1D) max pooling operation or attention-based operation only on the time-step dimension to obtain a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06639","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":"2026-05-18T00:57:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r1d243qrXlUuajPU6XjRwqj0DsSlgNIij36BynC8FI+5sJnzSEeUREVAbrAUJxSC9Rsr4M0Jam5eb71momS0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:22:36.508415Z"},"content_sha256":"54d1538eedb9356a4318f81c3987a9fa5c742fb13696abbe93539197801cd10c","schema_version":"1.0","event_id":"sha256:54d1538eedb9356a4318f81c3987a9fa5c742fb13696abbe93539197801cd10c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P2EZV3TOZON5MSIAD4SPQATOZS/bundle.json","state_url":"https://pith.science/pith/P2EZV3TOZON5MSIAD4SPQATOZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P2EZV3TOZON5MSIAD4SPQATOZS/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":"2026-06-01T06:22:36Z","links":{"resolver":"https://pith.science/pith/P2EZV3TOZON5MSIAD4SPQATOZS","bundle":"https://pith.science/pith/P2EZV3TOZON5MSIAD4SPQATOZS/bundle.json","state":"https://pith.science/pith/P2EZV3TOZON5MSIAD4SPQATOZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P2EZV3TOZON5MSIAD4SPQATOZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:P2EZV3TOZON5MSIAD4SPQATOZS","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":"f0d3493965af10de6642c808c9ac631d002b268341cd496a174c60d16bf76a16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-21T03:26:29Z","title_canon_sha256":"a7cefdb22c8474a7c886364b54f834d92dd94b239084074a3f4e967944472e63"},"schema_version":"1.0","source":{"id":"1611.06639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06639","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06639v1","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06639","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"pith_short_12","alias_value":"P2EZV3TOZON5","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"P2EZV3TOZON5MSIA","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"P2EZV3TO","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:54d1538eedb9356a4318f81c3987a9fa5c742fb13696abbe93539197801cd10c","target":"graph","created_at":"2026-05-18T00:57:33Z","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":"Recurrent Neural Network (RNN) is one of the most popular architectures used in Natural Language Processsing (NLP) tasks because its recurrent structure is very suitable to process variable-length text. RNN can utilize distributed representations of words by first converting the tokens comprising each text into vectors, which form a matrix. And this matrix includes two dimensions: the time-step dimension and the feature vector dimension. Then most existing models usually utilize one-dimensional (1D) max pooling operation or attention-based operation only on the time-step dimension to obtain a ","authors_text":"Bo Xu, Hongyun Bao, Jiaming Xu, Peng Zhou, Suncong Zheng, Zhenyu Qi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-21T03:26:29Z","title":"Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06639","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":"sha256:6e14ec8452f8a1c4168e3f960cf7e713ad14631f3046bb2cec5c07fae22de78c","target":"record","created_at":"2026-05-18T00:57:33Z","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":"f0d3493965af10de6642c808c9ac631d002b268341cd496a174c60d16bf76a16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-21T03:26:29Z","title_canon_sha256":"a7cefdb22c8474a7c886364b54f834d92dd94b239084074a3f4e967944472e63"},"schema_version":"1.0","source":{"id":"1611.06639","kind":"arxiv","version":1}},"canonical_sha256":"7e899aee6ecb9bd649001f24f8026eccad0be3fc2d1dfc0ada1a4530c14381c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e899aee6ecb9bd649001f24f8026eccad0be3fc2d1dfc0ada1a4530c14381c2","first_computed_at":"2026-05-18T00:57:33.305406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:57:33.305406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sXaJVWTwAs6Kl2WEkka/LuPu/a/HrnQdzBd0A/hJ7Bs132bsKmot7wuwR2xKln8laV5ArOJbC/mGjyLQqWEJBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:57:33.305966Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.06639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e14ec8452f8a1c4168e3f960cf7e713ad14631f3046bb2cec5c07fae22de78c","sha256:54d1538eedb9356a4318f81c3987a9fa5c742fb13696abbe93539197801cd10c"],"state_sha256":"496cd4295075442a664a368551d0bcd8eb14cefc0b7b81223b290ed6235e8c90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O85RYxSbc2sAvaJpQ0Xe2WXI6/9THmcf/I0fO/d7pLb4qrmI3jk6ak1CqvNzdDv+/BAGIX49D7+wImPsj+bDAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:22:36.510367Z","bundle_sha256":"1d2be5e5c047c144cfe2db589fa55a93a21aa697b1ff185d8033663df4846513"}}