{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RDBDALJ2TYRCCHKLTUMW7MYJNC","short_pith_number":"pith:RDBDALJ2","canonical_record":{"source":{"id":"1708.05997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-20T17:48:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e231338f87d7f51b8382085453b0ac425ab285ecd32439d6b2a17e79bb736d05","abstract_canon_sha256":"5020d26a2c5b3ca263a09c04a89926c39c5969a7609806fdd529c5effde97b09"},"schema_version":"1.0"},"canonical_sha256":"88c2302d3a9e22211d4b9d196fb30968b4b1f61991a26432ed424249f5312b56","source":{"kind":"arxiv","id":"1708.05997","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.05997","created_at":"2026-05-18T00:37:33Z"},{"alias_kind":"arxiv_version","alias_value":"1708.05997v2","created_at":"2026-05-18T00:37:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05997","created_at":"2026-05-18T00:37:33Z"},{"alias_kind":"pith_short_12","alias_value":"RDBDALJ2TYRC","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RDBDALJ2TYRCCHKL","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RDBDALJ2","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RDBDALJ2TYRCCHKLTUMW7MYJNC","target":"record","payload":{"canonical_record":{"source":{"id":"1708.05997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-20T17:48:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e231338f87d7f51b8382085453b0ac425ab285ecd32439d6b2a17e79bb736d05","abstract_canon_sha256":"5020d26a2c5b3ca263a09c04a89926c39c5969a7609806fdd529c5effde97b09"},"schema_version":"1.0"},"canonical_sha256":"88c2302d3a9e22211d4b9d196fb30968b4b1f61991a26432ed424249f5312b56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:33.262939Z","signature_b64":"MqTaMkSrotJpTxDlYpj5ur1cNt+5Vx18JV+EGxncraUmP29Fd0no0n5hSkIIDw+VgLYdacxMWQRKjDWD1yrtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88c2302d3a9e22211d4b9d196fb30968b4b1f61991a26432ed424249f5312b56","last_reissued_at":"2026-05-18T00:37:33.262525Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:33.262525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.05997","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":"2026-05-18T00:37:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"234fCwDrtO39gZhJFKOYLFGCzX0oM97soY085VjIAmsAulhI0/fjf99ISxnnhINJHOw2s2z4AW6DB0eAECbmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T11:39:19.058546Z"},"content_sha256":"fcbc4ab968b2a29ba973d78fecc7c22742393d6b32ca28ede16ef3cd87275931","schema_version":"1.0","event_id":"sha256:fcbc4ab968b2a29ba973d78fecc7c22742393d6b32ca28ede16ef3cd87275931"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RDBDALJ2TYRCCHKLTUMW7MYJNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Batch Noise Contrastive Estimation Approach for Training Large Vocabulary Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dietrich Klakow, Youssef Oualil","submitted_at":"2017-08-20T17:48:35Z","abstract_excerpt":"Training large vocabulary Neural Network Language Models (NNLMs) is a difficult task due to the explicit requirement of the output layer normalization, which typically involves the evaluation of the full softmax function over the complete vocabulary. This paper proposes a Batch Noise Contrastive Estimation (B-NCE) approach to alleviate this problem. This is achieved by reducing the vocabulary, at each time step, to the target words in the batch and then replacing the softmax by the noise contrastive estimation approach, where these words play the role of targets and noise samples at the same t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05997","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":"2026-05-18T00:37:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LRRUZ12SAYkGc/hfGvIwJK9XYD/ISlYcz58/ElzYf8aOP302lCZ7AHPMe+kC8qJ23HPrSp0Ki/khuWzXgh4dCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T11:39:19.058889Z"},"content_sha256":"b949e1841cbd5506ecc43a63e08d32ce66620a0d93df6e25b7e6ca18df1c39d0","schema_version":"1.0","event_id":"sha256:b949e1841cbd5506ecc43a63e08d32ce66620a0d93df6e25b7e6ca18df1c39d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDBDALJ2TYRCCHKLTUMW7MYJNC/bundle.json","state_url":"https://pith.science/pith/RDBDALJ2TYRCCHKLTUMW7MYJNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDBDALJ2TYRCCHKLTUMW7MYJNC/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":"2026-07-10T11:39:19Z","links":{"resolver":"https://pith.science/pith/RDBDALJ2TYRCCHKLTUMW7MYJNC","bundle":"https://pith.science/pith/RDBDALJ2TYRCCHKLTUMW7MYJNC/bundle.json","state":"https://pith.science/pith/RDBDALJ2TYRCCHKLTUMW7MYJNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDBDALJ2TYRCCHKLTUMW7MYJNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RDBDALJ2TYRCCHKLTUMW7MYJNC","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":"5020d26a2c5b3ca263a09c04a89926c39c5969a7609806fdd529c5effde97b09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-20T17:48:35Z","title_canon_sha256":"e231338f87d7f51b8382085453b0ac425ab285ecd32439d6b2a17e79bb736d05"},"schema_version":"1.0","source":{"id":"1708.05997","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.05997","created_at":"2026-05-18T00:37:33Z"},{"alias_kind":"arxiv_version","alias_value":"1708.05997v2","created_at":"2026-05-18T00:37:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05997","created_at":"2026-05-18T00:37:33Z"},{"alias_kind":"pith_short_12","alias_value":"RDBDALJ2TYRC","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RDBDALJ2TYRCCHKL","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RDBDALJ2","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:b949e1841cbd5506ecc43a63e08d32ce66620a0d93df6e25b7e6ca18df1c39d0","target":"graph","created_at":"2026-05-18T00:37:33Z","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":"Training large vocabulary Neural Network Language Models (NNLMs) is a difficult task due to the explicit requirement of the output layer normalization, which typically involves the evaluation of the full softmax function over the complete vocabulary. This paper proposes a Batch Noise Contrastive Estimation (B-NCE) approach to alleviate this problem. This is achieved by reducing the vocabulary, at each time step, to the target words in the batch and then replacing the softmax by the noise contrastive estimation approach, where these words play the role of targets and noise samples at the same t","authors_text":"Dietrich Klakow, Youssef Oualil","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-20T17:48:35Z","title":"A Batch Noise Contrastive Estimation Approach for Training Large Vocabulary Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05997","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:fcbc4ab968b2a29ba973d78fecc7c22742393d6b32ca28ede16ef3cd87275931","target":"record","created_at":"2026-05-18T00:37:33Z","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":"5020d26a2c5b3ca263a09c04a89926c39c5969a7609806fdd529c5effde97b09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-20T17:48:35Z","title_canon_sha256":"e231338f87d7f51b8382085453b0ac425ab285ecd32439d6b2a17e79bb736d05"},"schema_version":"1.0","source":{"id":"1708.05997","kind":"arxiv","version":2}},"canonical_sha256":"88c2302d3a9e22211d4b9d196fb30968b4b1f61991a26432ed424249f5312b56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88c2302d3a9e22211d4b9d196fb30968b4b1f61991a26432ed424249f5312b56","first_computed_at":"2026-05-18T00:37:33.262525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:33.262525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MqTaMkSrotJpTxDlYpj5ur1cNt+5Vx18JV+EGxncraUmP29Fd0no0n5hSkIIDw+VgLYdacxMWQRKjDWD1yrtDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:33.262939Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.05997","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcbc4ab968b2a29ba973d78fecc7c22742393d6b32ca28ede16ef3cd87275931","sha256:b949e1841cbd5506ecc43a63e08d32ce66620a0d93df6e25b7e6ca18df1c39d0"],"state_sha256":"89042c7a2e09f49eaf9b557bf61c02d57f053de842066a13d1d0fb0607dda6be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8H0mngqNz5IE2BNnrSNZLVKJqeuZoapS6gr/alKC4bZ0D/BSn/Y2jljxLw/TMOmrhff7nOKLG7oWBRLbH/gAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T11:39:19.060658Z","bundle_sha256":"6cc8348f4bf47ed8bed24e8b17291d7898d1b23f7b9f66de8ac0d3cf2cd25bc6"}}