{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:FYXTDJSQB2HBJH4QTIX2ORN5MJ","short_pith_number":"pith:FYXTDJSQ","canonical_record":{"source":{"id":"1610.09893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-31T12:24:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"40309dfb9311c66bf181c9cf8d8fc73f25c96d938105c093b979d19da888a62e","abstract_canon_sha256":"9629faf25644a7c8cb70bc347ca99846194f04e86ae842612e253cb59a4eff40"},"schema_version":"1.0"},"canonical_sha256":"2e2f31a6500e8e149f909a2fa745bd62666034d6ae6e850c4065d87295d549ca","source":{"kind":"arxiv","id":"1610.09893","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.09893","created_at":"2026-05-18T01:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"1610.09893v1","created_at":"2026-05-18T01:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09893","created_at":"2026-05-18T01:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"FYXTDJSQB2HB","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FYXTDJSQB2HBJH4Q","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FYXTDJSQ","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:FYXTDJSQB2HBJH4QTIX2ORN5MJ","target":"record","payload":{"canonical_record":{"source":{"id":"1610.09893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-31T12:24:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"40309dfb9311c66bf181c9cf8d8fc73f25c96d938105c093b979d19da888a62e","abstract_canon_sha256":"9629faf25644a7c8cb70bc347ca99846194f04e86ae842612e253cb59a4eff40"},"schema_version":"1.0"},"canonical_sha256":"2e2f31a6500e8e149f909a2fa745bd62666034d6ae6e850c4065d87295d549ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:46.958676Z","signature_b64":"E6Uae0b26exZKHOt95mZxmgjrldPv27NJ4L/FIJHP//IdUWUVGzAnu5rVUvP9wXIM0ezS/BbW0sEp2fOdiYNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e2f31a6500e8e149f909a2fa745bd62666034d6ae6e850c4065d87295d549ca","last_reissued_at":"2026-05-18T01:00:46.958255Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:46.958255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.09893","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":"2026-05-18T01:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qx5wYdqhF072V9ieJ+Ne8pYysw4Ynp/g4yF615ixt6oR+MvF1g1IXVdMaB36yUtZhStc62VTGq4O+60CRb/mCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T06:11:09.169820Z"},"content_sha256":"05b7642446a0568e45ec3ee3ee4af9949208ff5c1fd29e95e91f23122b349e1b","schema_version":"1.0","event_id":"sha256:05b7642446a0568e45ec3ee3ee4af9949208ff5c1fd29e95e91f23122b349e1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:FYXTDJSQB2HBJH4QTIX2ORN5MJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LightRNN: Memory and Computation-Efficient Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jian Yang, Tao Qin, Tie-Yan Liu, Xiang Li","submitted_at":"2016-10-31T12:24:13Z","abstract_excerpt":"Recurrent neural networks (RNNs) have achieved state-of-the-art performances in many natural language processing tasks, such as language modeling and machine translation. However, when the vocabulary is large, the RNN model will become very big (e.g., possibly beyond the memory capacity of a GPU device) and its training will become very inefficient. In this work, we propose a novel technique to tackle this challenge. The key idea is to use 2-Component (2C) shared embedding for word representations. We allocate every word in the vocabulary into a table, each row of which is associated with a ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09893","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":"2026-05-18T01:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKWO85sZyNdJkQrGT6cL0QYoU0iggAjkORKc/QNbhSFBtMOi1SZGcN4hBS90IaJ1elClWa90NMBbLoWW/3EkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T06:11:09.170167Z"},"content_sha256":"73cf6f17936cc83c82ba7940067e12cbc0fca13f447a10c3ae60c0bd8106b5f7","schema_version":"1.0","event_id":"sha256:73cf6f17936cc83c82ba7940067e12cbc0fca13f447a10c3ae60c0bd8106b5f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FYXTDJSQB2HBJH4QTIX2ORN5MJ/bundle.json","state_url":"https://pith.science/pith/FYXTDJSQB2HBJH4QTIX2ORN5MJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FYXTDJSQB2HBJH4QTIX2ORN5MJ/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":"2026-05-28T06:11:09Z","links":{"resolver":"https://pith.science/pith/FYXTDJSQB2HBJH4QTIX2ORN5MJ","bundle":"https://pith.science/pith/FYXTDJSQB2HBJH4QTIX2ORN5MJ/bundle.json","state":"https://pith.science/pith/FYXTDJSQB2HBJH4QTIX2ORN5MJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FYXTDJSQB2HBJH4QTIX2ORN5MJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:FYXTDJSQB2HBJH4QTIX2ORN5MJ","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":"9629faf25644a7c8cb70bc347ca99846194f04e86ae842612e253cb59a4eff40","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-31T12:24:13Z","title_canon_sha256":"40309dfb9311c66bf181c9cf8d8fc73f25c96d938105c093b979d19da888a62e"},"schema_version":"1.0","source":{"id":"1610.09893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.09893","created_at":"2026-05-18T01:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"1610.09893v1","created_at":"2026-05-18T01:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09893","created_at":"2026-05-18T01:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"FYXTDJSQB2HB","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FYXTDJSQB2HBJH4Q","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FYXTDJSQ","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:73cf6f17936cc83c82ba7940067e12cbc0fca13f447a10c3ae60c0bd8106b5f7","target":"graph","created_at":"2026-05-18T01:00:46Z","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":"Recurrent neural networks (RNNs) have achieved state-of-the-art performances in many natural language processing tasks, such as language modeling and machine translation. However, when the vocabulary is large, the RNN model will become very big (e.g., possibly beyond the memory capacity of a GPU device) and its training will become very inefficient. In this work, we propose a novel technique to tackle this challenge. The key idea is to use 2-Component (2C) shared embedding for word representations. We allocate every word in the vocabulary into a table, each row of which is associated with a ve","authors_text":"Jian Yang, Tao Qin, Tie-Yan Liu, Xiang Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-31T12:24:13Z","title":"LightRNN: Memory and Computation-Efficient Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09893","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":"sha256:05b7642446a0568e45ec3ee3ee4af9949208ff5c1fd29e95e91f23122b349e1b","target":"record","created_at":"2026-05-18T01:00:46Z","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":"9629faf25644a7c8cb70bc347ca99846194f04e86ae842612e253cb59a4eff40","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-31T12:24:13Z","title_canon_sha256":"40309dfb9311c66bf181c9cf8d8fc73f25c96d938105c093b979d19da888a62e"},"schema_version":"1.0","source":{"id":"1610.09893","kind":"arxiv","version":1}},"canonical_sha256":"2e2f31a6500e8e149f909a2fa745bd62666034d6ae6e850c4065d87295d549ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e2f31a6500e8e149f909a2fa745bd62666034d6ae6e850c4065d87295d549ca","first_computed_at":"2026-05-18T01:00:46.958255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:46.958255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E6Uae0b26exZKHOt95mZxmgjrldPv27NJ4L/FIJHP//IdUWUVGzAnu5rVUvP9wXIM0ezS/BbW0sEp2fOdiYNAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:46.958676Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.09893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05b7642446a0568e45ec3ee3ee4af9949208ff5c1fd29e95e91f23122b349e1b","sha256:73cf6f17936cc83c82ba7940067e12cbc0fca13f447a10c3ae60c0bd8106b5f7"],"state_sha256":"9cd768998fffe484d15787e900c6d91505bc1cd5ba1dfc0481ac261167dbaa4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0NBeS3PpWh4WsIAXG+JcG2VyZH9briLafdtlye2lEOrDv+CoKvywny3hORcYotTsu06Bv2o7DzaWoj+lH5F7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T06:11:09.172139Z","bundle_sha256":"6cd692e13b2b632ec33b4019187985e4c057fcc96c1a0d23625462062c96fc92"}}