{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VT6LSNMQEXNFBQBAQ2XAHBRWRT","short_pith_number":"pith:VT6LSNMQ","canonical_record":{"source":{"id":"1709.00659","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T04:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"bac6c35eb0a2e40aedfc42af2c64139bb2b9c4d21ab8821ffdeb6973b9da4036","abstract_canon_sha256":"5f642b532f61d411db6950b20447b91b78ad3b2176b588d3efb0b026152e6d37"},"schema_version":"1.0"},"canonical_sha256":"acfcb9359025da50c02086ae0386368cc5154463742b6735956be285b038b08a","source":{"kind":"arxiv","id":"1709.00659","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00659","created_at":"2026-05-18T00:29:18Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00659v2","created_at":"2026-05-18T00:29:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00659","created_at":"2026-05-18T00:29:18Z"},{"alias_kind":"pith_short_12","alias_value":"VT6LSNMQEXNF","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VT6LSNMQEXNFBQBA","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VT6LSNMQ","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VT6LSNMQEXNFBQBAQ2XAHBRWRT","target":"record","payload":{"canonical_record":{"source":{"id":"1709.00659","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T04:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"bac6c35eb0a2e40aedfc42af2c64139bb2b9c4d21ab8821ffdeb6973b9da4036","abstract_canon_sha256":"5f642b532f61d411db6950b20447b91b78ad3b2176b588d3efb0b026152e6d37"},"schema_version":"1.0"},"canonical_sha256":"acfcb9359025da50c02086ae0386368cc5154463742b6735956be285b038b08a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:18.381971Z","signature_b64":"nuFxdHMusIC9MPTjs9yOTOii2rmEkixrRENIO3tsMgg9UJ9wcCvoobKS2LPxvVqf1wrsmOQ5ff9Bj8ztskWxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acfcb9359025da50c02086ae0386368cc5154463742b6735956be285b038b08a","last_reissued_at":"2026-05-18T00:29:18.381335Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:18.381335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.00659","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":"2026-05-18T00:29:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W5mwGC84Z5lxI4nJr/cpIq1u1F9kFpnfJE830fIMU3LRj9VsByHctyrH6a+/YT5HGKKiDCuiyewHH6MraqWrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T13:52:09.204748Z"},"content_sha256":"5ed342d35a67f69c4d71f8d27219d82b3bce72aa1990af3d096030b3ccc5042f","schema_version":"1.0","event_id":"sha256:5ed342d35a67f69c4d71f8d27219d82b3bce72aa1990af3d096030b3ccc5042f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VT6LSNMQEXNFBQBAQ2XAHBRWRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating how well contextual features are captured by bi-directional recurrent neural network models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Anand, Kushal Chawla, Sunil Kumar Sahu","submitted_at":"2017-09-03T04:00:49Z","abstract_excerpt":"Learning algorithms for natural language processing (NLP) tasks traditionally rely on manually defined relevant contextual features. On the other hand, neural network models using an only distributional representation of words have been successfully applied for several NLP tasks. Such models learn features automatically and avoid explicit feature engineering. Across several domains, neural models become a natural choice specifically when limited characteristics of data are known. However, this flexibility comes at the cost of interpretability. In this paper, we define three different methods t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00659","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":"2026-05-18T00:29:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CeBmKYv9R+gIJcV21mS7MdaC/3YWHjuYq6UkypLOWKxrAyAq5VGwoGe3H+zp8RNSiMBnKpFQsQebpDccTAG2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T13:52:09.205095Z"},"content_sha256":"084e7be3b2977ffc81ff089df41894e4f914fdd3bd23ef08d0879a96459ca75a","schema_version":"1.0","event_id":"sha256:084e7be3b2977ffc81ff089df41894e4f914fdd3bd23ef08d0879a96459ca75a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VT6LSNMQEXNFBQBAQ2XAHBRWRT/bundle.json","state_url":"https://pith.science/pith/VT6LSNMQEXNFBQBAQ2XAHBRWRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VT6LSNMQEXNFBQBAQ2XAHBRWRT/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":"2026-06-08T13:52:09Z","links":{"resolver":"https://pith.science/pith/VT6LSNMQEXNFBQBAQ2XAHBRWRT","bundle":"https://pith.science/pith/VT6LSNMQEXNFBQBAQ2XAHBRWRT/bundle.json","state":"https://pith.science/pith/VT6LSNMQEXNFBQBAQ2XAHBRWRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VT6LSNMQEXNFBQBAQ2XAHBRWRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VT6LSNMQEXNFBQBAQ2XAHBRWRT","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":"5f642b532f61d411db6950b20447b91b78ad3b2176b588d3efb0b026152e6d37","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T04:00:49Z","title_canon_sha256":"bac6c35eb0a2e40aedfc42af2c64139bb2b9c4d21ab8821ffdeb6973b9da4036"},"schema_version":"1.0","source":{"id":"1709.00659","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00659","created_at":"2026-05-18T00:29:18Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00659v2","created_at":"2026-05-18T00:29:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00659","created_at":"2026-05-18T00:29:18Z"},{"alias_kind":"pith_short_12","alias_value":"VT6LSNMQEXNF","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VT6LSNMQEXNFBQBA","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VT6LSNMQ","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:084e7be3b2977ffc81ff089df41894e4f914fdd3bd23ef08d0879a96459ca75a","target":"graph","created_at":"2026-05-18T00:29:18Z","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":"Learning algorithms for natural language processing (NLP) tasks traditionally rely on manually defined relevant contextual features. On the other hand, neural network models using an only distributional representation of words have been successfully applied for several NLP tasks. Such models learn features automatically and avoid explicit feature engineering. Across several domains, neural models become a natural choice specifically when limited characteristics of data are known. However, this flexibility comes at the cost of interpretability. In this paper, we define three different methods t","authors_text":"Ashish Anand, Kushal Chawla, Sunil Kumar Sahu","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T04:00:49Z","title":"Investigating how well contextual features are captured by bi-directional recurrent neural network models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00659","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":"sha256:5ed342d35a67f69c4d71f8d27219d82b3bce72aa1990af3d096030b3ccc5042f","target":"record","created_at":"2026-05-18T00:29:18Z","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":"5f642b532f61d411db6950b20447b91b78ad3b2176b588d3efb0b026152e6d37","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T04:00:49Z","title_canon_sha256":"bac6c35eb0a2e40aedfc42af2c64139bb2b9c4d21ab8821ffdeb6973b9da4036"},"schema_version":"1.0","source":{"id":"1709.00659","kind":"arxiv","version":2}},"canonical_sha256":"acfcb9359025da50c02086ae0386368cc5154463742b6735956be285b038b08a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acfcb9359025da50c02086ae0386368cc5154463742b6735956be285b038b08a","first_computed_at":"2026-05-18T00:29:18.381335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:18.381335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nuFxdHMusIC9MPTjs9yOTOii2rmEkixrRENIO3tsMgg9UJ9wcCvoobKS2LPxvVqf1wrsmOQ5ff9Bj8ztskWxCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:18.381971Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00659","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ed342d35a67f69c4d71f8d27219d82b3bce72aa1990af3d096030b3ccc5042f","sha256:084e7be3b2977ffc81ff089df41894e4f914fdd3bd23ef08d0879a96459ca75a"],"state_sha256":"5873286c86a962e63c41c855cb71352fcb4c51c1aa6a54b6a6a404a8fea22a3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxrLhUHk0uvLDzXIWzALIfMHE9hOIdo1OsMdoPg2bhewdrUdLkouyUERueWdqZmGOaD3prcIpYc3SxsLKEGNAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T13:52:09.207251Z","bundle_sha256":"8983f450b4ba00c388fb02841385e76f5ca3ad4ed0cb26eec16c856fd5e6a94d"}}