{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3TNFS76KUONICM3MK5QJLHBFVD","short_pith_number":"pith:3TNFS76K","canonical_record":{"source":{"id":"1703.10724","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T01:21:40Z","cross_cats_sorted":[],"title_canon_sha256":"0d9c1a716746261ab3287454eb5e4aa7a6e79200a0d8d082d0c6e9a727245fba","abstract_canon_sha256":"e30dc31480f1b4c96412ede8d3b01900c24827a127fa145fc60226b22e414020"},"schema_version":"1.0"},"canonical_sha256":"dcda597fcaa39a81336c5760959c25a8ce42198f6a266cc1d19a1b2ecc242ff9","source":{"kind":"arxiv","id":"1703.10724","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10724","created_at":"2026-05-18T00:42:04Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10724v2","created_at":"2026-05-18T00:42:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10724","created_at":"2026-05-18T00:42:04Z"},{"alias_kind":"pith_short_12","alias_value":"3TNFS76KUONI","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3TNFS76KUONICM3M","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3TNFS76K","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3TNFS76KUONICM3MK5QJLHBFVD","target":"record","payload":{"canonical_record":{"source":{"id":"1703.10724","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T01:21:40Z","cross_cats_sorted":[],"title_canon_sha256":"0d9c1a716746261ab3287454eb5e4aa7a6e79200a0d8d082d0c6e9a727245fba","abstract_canon_sha256":"e30dc31480f1b4c96412ede8d3b01900c24827a127fa145fc60226b22e414020"},"schema_version":"1.0"},"canonical_sha256":"dcda597fcaa39a81336c5760959c25a8ce42198f6a266cc1d19a1b2ecc242ff9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:04.768639Z","signature_b64":"so7/SVUD5lBGAbI+L6EQgYw3H48fPRFJplRuRnIvE9/jpiueT9hdpiVs9YDGI13+WSdMdOBAcUBr8SZ4LNdrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcda597fcaa39a81336c5760959c25a8ce42198f6a266cc1d19a1b2ecc242ff9","last_reissued_at":"2026-05-18T00:42:04.767873Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:04.767873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.10724","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":"2026-05-18T00:42:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"utR1FRsz8cjQgo7/sdBNVKrBv3fUif9x29Wm2ckWwSQq5eX9YT2EZ5CKFV4mWk10EeVjbO00l5eTqzrcY42uCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:38:04.294533Z"},"content_sha256":"7f065efc78af93ec8db4325f6677a9197332009bab048e0cd6756754d69ca6d8","schema_version":"1.0","event_id":"sha256:7f065efc78af93ec8db4325f6677a9197332009bab048e0cd6756754d69ca6d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3TNFS76KUONICM3MK5QJLHBFVD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"N-gram Language Modeling using Recurrent Neural Network Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ciprian Chelba, Mohammad Norouzi, Samy Bengio","submitted_at":"2017-03-31T01:21:40Z","abstract_excerpt":"We investigate the effective memory depth of RNN models by using them for $n$-gram language model (LM) smoothing.\n  Experiments on a small corpus (UPenn Treebank, one million words of training data and 10k vocabulary) have found the LSTM cell with dropout to be the best model for encoding the $n$-gram state when compared with feed-forward and vanilla RNN models. When preserving the sentence independence assumption the LSTM $n$-gram matches the LSTM LM performance for $n=9$ and slightly outperforms it for $n=13$. When allowing dependencies across sentence boundaries, the LSTM $13$-gram almost m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10724","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":"2026-05-18T00:42:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DRbD3bWcgw8nxJvFwZVC3N3eLwlITpYJjYkYqi7Fnv8bUI6e/AXmGhry2ZYUMudofYADWtBvNGhw2KvZhFE0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:38:04.294890Z"},"content_sha256":"341ae46a7b8c3e5dcde0e54cfc6019e01aa316d65af9c2ad1eaad89455b8c229","schema_version":"1.0","event_id":"sha256:341ae46a7b8c3e5dcde0e54cfc6019e01aa316d65af9c2ad1eaad89455b8c229"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/bundle.json","state_url":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TNFS76KUONICM3MK5QJLHBFVD/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":"2026-06-02T21:38:04Z","links":{"resolver":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD","bundle":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/bundle.json","state":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TNFS76KUONICM3MK5QJLHBFVD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3TNFS76KUONICM3MK5QJLHBFVD","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":"e30dc31480f1b4c96412ede8d3b01900c24827a127fa145fc60226b22e414020","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T01:21:40Z","title_canon_sha256":"0d9c1a716746261ab3287454eb5e4aa7a6e79200a0d8d082d0c6e9a727245fba"},"schema_version":"1.0","source":{"id":"1703.10724","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10724","created_at":"2026-05-18T00:42:04Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10724v2","created_at":"2026-05-18T00:42:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10724","created_at":"2026-05-18T00:42:04Z"},{"alias_kind":"pith_short_12","alias_value":"3TNFS76KUONI","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3TNFS76KUONICM3M","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3TNFS76K","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:341ae46a7b8c3e5dcde0e54cfc6019e01aa316d65af9c2ad1eaad89455b8c229","target":"graph","created_at":"2026-05-18T00:42:04Z","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":"We investigate the effective memory depth of RNN models by using them for $n$-gram language model (LM) smoothing.\n  Experiments on a small corpus (UPenn Treebank, one million words of training data and 10k vocabulary) have found the LSTM cell with dropout to be the best model for encoding the $n$-gram state when compared with feed-forward and vanilla RNN models. When preserving the sentence independence assumption the LSTM $n$-gram matches the LSTM LM performance for $n=9$ and slightly outperforms it for $n=13$. When allowing dependencies across sentence boundaries, the LSTM $13$-gram almost m","authors_text":"Ciprian Chelba, Mohammad Norouzi, Samy Bengio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T01:21:40Z","title":"N-gram Language Modeling using Recurrent Neural Network Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10724","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":"sha256:7f065efc78af93ec8db4325f6677a9197332009bab048e0cd6756754d69ca6d8","target":"record","created_at":"2026-05-18T00:42:04Z","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":"e30dc31480f1b4c96412ede8d3b01900c24827a127fa145fc60226b22e414020","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T01:21:40Z","title_canon_sha256":"0d9c1a716746261ab3287454eb5e4aa7a6e79200a0d8d082d0c6e9a727245fba"},"schema_version":"1.0","source":{"id":"1703.10724","kind":"arxiv","version":2}},"canonical_sha256":"dcda597fcaa39a81336c5760959c25a8ce42198f6a266cc1d19a1b2ecc242ff9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcda597fcaa39a81336c5760959c25a8ce42198f6a266cc1d19a1b2ecc242ff9","first_computed_at":"2026-05-18T00:42:04.767873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:04.767873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"so7/SVUD5lBGAbI+L6EQgYw3H48fPRFJplRuRnIvE9/jpiueT9hdpiVs9YDGI13+WSdMdOBAcUBr8SZ4LNdrBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:04.768639Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.10724","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f065efc78af93ec8db4325f6677a9197332009bab048e0cd6756754d69ca6d8","sha256:341ae46a7b8c3e5dcde0e54cfc6019e01aa316d65af9c2ad1eaad89455b8c229"],"state_sha256":"3280fb5b5410bb07edd2e2a3a1ce7710cd287bc3ccd5fa1e38a40c38da39e99c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2ytCHRotNyyGL8yeR7iReAioqWhSLdfI99WsDxuHQrUN/lVxLREINIIM1YjSfrk/fzMeDLzeuy7Mlf6X1FzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T21:38:04.296732Z","bundle_sha256":"2383161587a02551508d2d38a48213c16a7294f20b4cfe8fc6cd2c63a07d9c9b"}}