{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QXCJQH3RCDCX7HNJPTNODE6TSB","short_pith_number":"pith:QXCJQH3R","canonical_record":{"source":{"id":"1708.05592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-18T13:11:22Z","cross_cats_sorted":[],"title_canon_sha256":"07988567ad0b70b36a96001a5dd4ef6a5d450d04918131386075ddbecfad0c89","abstract_canon_sha256":"cfe70cdf0cff9384aa73d98534a1a45058f56dfa4bdb865506e93249b3e375d8"},"schema_version":"1.0"},"canonical_sha256":"85c4981f7110c57f9da97cdae193d3905266c57ecf7cb91fe66bd4a966688e22","source":{"kind":"arxiv","id":"1708.05592","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.05592","created_at":"2026-05-18T00:37:49Z"},{"alias_kind":"arxiv_version","alias_value":"1708.05592v1","created_at":"2026-05-18T00:37:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05592","created_at":"2026-05-18T00:37:49Z"},{"alias_kind":"pith_short_12","alias_value":"QXCJQH3RCDCX","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QXCJQH3RCDCX7HNJ","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QXCJQH3R","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QXCJQH3RCDCX7HNJPTNODE6TSB","target":"record","payload":{"canonical_record":{"source":{"id":"1708.05592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-18T13:11:22Z","cross_cats_sorted":[],"title_canon_sha256":"07988567ad0b70b36a96001a5dd4ef6a5d450d04918131386075ddbecfad0c89","abstract_canon_sha256":"cfe70cdf0cff9384aa73d98534a1a45058f56dfa4bdb865506e93249b3e375d8"},"schema_version":"1.0"},"canonical_sha256":"85c4981f7110c57f9da97cdae193d3905266c57ecf7cb91fe66bd4a966688e22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:49.574405Z","signature_b64":"jox3Bf+vDPxA4S74GvcCrPJyB4IOXZk6ZRUhXxe8n9DuNetfhhPn6+hV3wtHq1SIA92mxexBrpYD8J6fT7/hDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85c4981f7110c57f9da97cdae193d3905266c57ecf7cb91fe66bd4a966688e22","last_reissued_at":"2026-05-18T00:37:49.573795Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:49.573795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.05592","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":"2026-05-18T00:37:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IyfgMnHZrGHHuIlHZ6DYvOz+JMgvF+7qBQWZ13SGaMzQraAjcL2hdQ4WkHsNuYHYvWyEklHg5Hy+apOXovSvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:10:49.225210Z"},"content_sha256":"08b9d4d71431c8239611c987b54b248a0351fad898ae06adbe803e1f0e18926b","schema_version":"1.0","event_id":"sha256:08b9d4d71431c8239611c987b54b248a0351fad898ae06adbe803e1f0e18926b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QXCJQH3RCDCX7HNJPTNODE6TSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Future Word Contexts in Neural Network Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anton Ragni, Mark Gales, Xie Chen, Xunying Liu, Yu Wang","submitted_at":"2017-08-18T13:11:22Z","abstract_excerpt":"Recently, bidirectional recurrent network language models (bi-RNNLMs) have been shown to outperform standard, unidirectional, recurrent neural network language models (uni-RNNLMs) on a range of speech recognition tasks. This indicates that future word context information beyond the word history can be useful. However, bi-RNNLMs pose a number of challenges as they make use of the complete previous and future word context information. This impacts both training efficiency and their use within a lattice rescoring framework. In this paper these issues are addressed by proposing a novel neural netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05592","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":"2026-05-18T00:37:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NV6KnTxdz/SB7RmOaWYsQMmaMBJAbQ2XbDCZ2SvJ5WKYrZ8DSC7Ma67hP3rgbEJYM6D5Y3NqjMdqCuMy/jMGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:10:49.225575Z"},"content_sha256":"f1d33819529f9407e122ee7394690afe71d36fbef4b791bc1aa3cd3b155e9ecc","schema_version":"1.0","event_id":"sha256:f1d33819529f9407e122ee7394690afe71d36fbef4b791bc1aa3cd3b155e9ecc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXCJQH3RCDCX7HNJPTNODE6TSB/bundle.json","state_url":"https://pith.science/pith/QXCJQH3RCDCX7HNJPTNODE6TSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXCJQH3RCDCX7HNJPTNODE6TSB/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":"2026-06-04T20:10:49Z","links":{"resolver":"https://pith.science/pith/QXCJQH3RCDCX7HNJPTNODE6TSB","bundle":"https://pith.science/pith/QXCJQH3RCDCX7HNJPTNODE6TSB/bundle.json","state":"https://pith.science/pith/QXCJQH3RCDCX7HNJPTNODE6TSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXCJQH3RCDCX7HNJPTNODE6TSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QXCJQH3RCDCX7HNJPTNODE6TSB","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":"cfe70cdf0cff9384aa73d98534a1a45058f56dfa4bdb865506e93249b3e375d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-18T13:11:22Z","title_canon_sha256":"07988567ad0b70b36a96001a5dd4ef6a5d450d04918131386075ddbecfad0c89"},"schema_version":"1.0","source":{"id":"1708.05592","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.05592","created_at":"2026-05-18T00:37:49Z"},{"alias_kind":"arxiv_version","alias_value":"1708.05592v1","created_at":"2026-05-18T00:37:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05592","created_at":"2026-05-18T00:37:49Z"},{"alias_kind":"pith_short_12","alias_value":"QXCJQH3RCDCX","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QXCJQH3RCDCX7HNJ","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QXCJQH3R","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:f1d33819529f9407e122ee7394690afe71d36fbef4b791bc1aa3cd3b155e9ecc","target":"graph","created_at":"2026-05-18T00:37:49Z","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":"Recently, bidirectional recurrent network language models (bi-RNNLMs) have been shown to outperform standard, unidirectional, recurrent neural network language models (uni-RNNLMs) on a range of speech recognition tasks. This indicates that future word context information beyond the word history can be useful. However, bi-RNNLMs pose a number of challenges as they make use of the complete previous and future word context information. This impacts both training efficiency and their use within a lattice rescoring framework. In this paper these issues are addressed by proposing a novel neural netw","authors_text":"Anton Ragni, Mark Gales, Xie Chen, Xunying Liu, Yu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-18T13:11:22Z","title":"Future Word Contexts in Neural Network Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05592","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":"sha256:08b9d4d71431c8239611c987b54b248a0351fad898ae06adbe803e1f0e18926b","target":"record","created_at":"2026-05-18T00:37:49Z","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":"cfe70cdf0cff9384aa73d98534a1a45058f56dfa4bdb865506e93249b3e375d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-18T13:11:22Z","title_canon_sha256":"07988567ad0b70b36a96001a5dd4ef6a5d450d04918131386075ddbecfad0c89"},"schema_version":"1.0","source":{"id":"1708.05592","kind":"arxiv","version":1}},"canonical_sha256":"85c4981f7110c57f9da97cdae193d3905266c57ecf7cb91fe66bd4a966688e22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85c4981f7110c57f9da97cdae193d3905266c57ecf7cb91fe66bd4a966688e22","first_computed_at":"2026-05-18T00:37:49.573795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:49.573795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jox3Bf+vDPxA4S74GvcCrPJyB4IOXZk6ZRUhXxe8n9DuNetfhhPn6+hV3wtHq1SIA92mxexBrpYD8J6fT7/hDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:49.574405Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.05592","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08b9d4d71431c8239611c987b54b248a0351fad898ae06adbe803e1f0e18926b","sha256:f1d33819529f9407e122ee7394690afe71d36fbef4b791bc1aa3cd3b155e9ecc"],"state_sha256":"840fa777876e0e8aa0f1715461632c5ded913382b74d3a0f7f678e5691b8f07a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kf2EsGngSTsow3cjJr7ka2ker93xPI3YfeRHYOUbPJJlG+hA2uOUaS3DRWMxA473J74OfRkMnrfg49pg+MFPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T20:10:49.227669Z","bundle_sha256":"beaeb830dd9b554cbd2e58e88efba1c3df486b3e7ab44ab45507b8c27cc1a995"}}