{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DA56ENYPWGJPQPN3TXZK3XEGYX","short_pith_number":"pith:DA56ENYP","canonical_record":{"source":{"id":"1806.04189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-11T18:57:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d23b77df390cce2e1a219a25def61bee7f240b703100ba8b420b4f93286d0822","abstract_canon_sha256":"99b542fccc3c99931dcb668c52de80c2d160e3db763bece7a7f90b811af13991"},"schema_version":"1.0"},"canonical_sha256":"183be2370fb192f83dbb9df2addc86c5dc8cdbab8cef41632ab5e2e92fc92f75","source":{"kind":"arxiv","id":"1806.04189","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04189","created_at":"2026-05-18T00:13:36Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04189v1","created_at":"2026-05-18T00:13:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04189","created_at":"2026-05-18T00:13:36Z"},{"alias_kind":"pith_short_12","alias_value":"DA56ENYPWGJP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DA56ENYPWGJPQPN3","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DA56ENYP","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DA56ENYPWGJPQPN3TXZK3XEGYX","target":"record","payload":{"canonical_record":{"source":{"id":"1806.04189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-11T18:57:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d23b77df390cce2e1a219a25def61bee7f240b703100ba8b420b4f93286d0822","abstract_canon_sha256":"99b542fccc3c99931dcb668c52de80c2d160e3db763bece7a7f90b811af13991"},"schema_version":"1.0"},"canonical_sha256":"183be2370fb192f83dbb9df2addc86c5dc8cdbab8cef41632ab5e2e92fc92f75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:36.339867Z","signature_b64":"+ZuOLeEi5dFgVFLenmWdBf/Do1nKVJjTDM10uMvj7TJQRSldNGa1iLYFYocvlBqRHw/CQ+GVRORdKMBp+apbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"183be2370fb192f83dbb9df2addc86c5dc8cdbab8cef41632ab5e2e92fc92f75","last_reissued_at":"2026-05-18T00:13:36.339174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:36.339174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.04189","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":"2026-05-18T00:13:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8R6Ei8GCVSRJf0fTCijioCypPBS7pkwnAz5VbpoPgwS2nYKuRljterUuk8NrQNBpR15it9FbmNB9kGT/Yl4bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:01:06.066400Z"},"content_sha256":"bc5ce0c6a4df990ed4be982eff97ef04546bf04da6e286f7ce8040bd0dd33f0b","schema_version":"1.0","event_id":"sha256:bc5ce0c6a4df990ed4be982eff97ef04546bf04da6e286f7ce8040bd0dd33f0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DA56ENYPWGJPQPN3TXZK3XEGYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Minjia Zhang, Wenhan Wang, XiaoDong Liu, Yuxiong He","submitted_at":"2018-06-11T18:57:49Z","abstract_excerpt":"Neural language models (NLMs) have recently gained a renewed interest by achieving state-of-the-art performance across many natural language processing (NLP) tasks. However, NLMs are very computationally demanding largely due to the computational cost of the softmax layer over a large vocabulary. We observe that, in decoding of many NLP tasks, only the probabilities of the top-K hypotheses need to be calculated preciously and K is often much smaller than the vocabulary size. This paper proposes a novel softmax layer approximation algorithm, called Fast Graph Decoder (FGD), which quickly identi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04189","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":"2026-05-18T00:13:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHMsqKbNq1q/M7ZaSmwIB8aVPbsDvOT7p2c5RtZgnMnZuCF3olKjPBs5TCa5U4WeYA2BREOH9H0WWvqhk4L4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:01:06.067053Z"},"content_sha256":"c26f5eb0d2d999f1fb0dbab31a3f45da99ee588b2459462e2e8e09ae10341e94","schema_version":"1.0","event_id":"sha256:c26f5eb0d2d999f1fb0dbab31a3f45da99ee588b2459462e2e8e09ae10341e94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DA56ENYPWGJPQPN3TXZK3XEGYX/bundle.json","state_url":"https://pith.science/pith/DA56ENYPWGJPQPN3TXZK3XEGYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DA56ENYPWGJPQPN3TXZK3XEGYX/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":"2026-05-29T18:01:06Z","links":{"resolver":"https://pith.science/pith/DA56ENYPWGJPQPN3TXZK3XEGYX","bundle":"https://pith.science/pith/DA56ENYPWGJPQPN3TXZK3XEGYX/bundle.json","state":"https://pith.science/pith/DA56ENYPWGJPQPN3TXZK3XEGYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DA56ENYPWGJPQPN3TXZK3XEGYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DA56ENYPWGJPQPN3TXZK3XEGYX","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":"99b542fccc3c99931dcb668c52de80c2d160e3db763bece7a7f90b811af13991","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-11T18:57:49Z","title_canon_sha256":"d23b77df390cce2e1a219a25def61bee7f240b703100ba8b420b4f93286d0822"},"schema_version":"1.0","source":{"id":"1806.04189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04189","created_at":"2026-05-18T00:13:36Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04189v1","created_at":"2026-05-18T00:13:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04189","created_at":"2026-05-18T00:13:36Z"},{"alias_kind":"pith_short_12","alias_value":"DA56ENYPWGJP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DA56ENYPWGJPQPN3","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DA56ENYP","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:c26f5eb0d2d999f1fb0dbab31a3f45da99ee588b2459462e2e8e09ae10341e94","target":"graph","created_at":"2026-05-18T00:13:36Z","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":"Neural language models (NLMs) have recently gained a renewed interest by achieving state-of-the-art performance across many natural language processing (NLP) tasks. However, NLMs are very computationally demanding largely due to the computational cost of the softmax layer over a large vocabulary. We observe that, in decoding of many NLP tasks, only the probabilities of the top-K hypotheses need to be calculated preciously and K is often much smaller than the vocabulary size. This paper proposes a novel softmax layer approximation algorithm, called Fast Graph Decoder (FGD), which quickly identi","authors_text":"Jianfeng Gao, Minjia Zhang, Wenhan Wang, XiaoDong Liu, Yuxiong He","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-11T18:57:49Z","title":"Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04189","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:bc5ce0c6a4df990ed4be982eff97ef04546bf04da6e286f7ce8040bd0dd33f0b","target":"record","created_at":"2026-05-18T00:13:36Z","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":"99b542fccc3c99931dcb668c52de80c2d160e3db763bece7a7f90b811af13991","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-11T18:57:49Z","title_canon_sha256":"d23b77df390cce2e1a219a25def61bee7f240b703100ba8b420b4f93286d0822"},"schema_version":"1.0","source":{"id":"1806.04189","kind":"arxiv","version":1}},"canonical_sha256":"183be2370fb192f83dbb9df2addc86c5dc8cdbab8cef41632ab5e2e92fc92f75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"183be2370fb192f83dbb9df2addc86c5dc8cdbab8cef41632ab5e2e92fc92f75","first_computed_at":"2026-05-18T00:13:36.339174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:36.339174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ZuOLeEi5dFgVFLenmWdBf/Do1nKVJjTDM10uMvj7TJQRSldNGa1iLYFYocvlBqRHw/CQ+GVRORdKMBp+apbDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:36.339867Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc5ce0c6a4df990ed4be982eff97ef04546bf04da6e286f7ce8040bd0dd33f0b","sha256:c26f5eb0d2d999f1fb0dbab31a3f45da99ee588b2459462e2e8e09ae10341e94"],"state_sha256":"b85200daba43167aa38e5724f8e1c417bebeac3adf1349d5718a8aba415cae91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXgmvn9z74pR6T0t2vg5/DdKDOsuaXs0DAt9vjg+/+KXAvPXoTJioQPNOWXegbTSfXL0OMo2QEqpxhnokUutDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:01:06.070786Z","bundle_sha256":"7072fad32d1af84403b8b68a5f4a491fa0a2ff217caf0371d74001ca23178bd5"}}