{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6I4DRVKV4G3TYE236Y5PMNQQNU","short_pith_number":"pith:6I4DRVKV","canonical_record":{"source":{"id":"1802.02615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-07T19:43:01Z","cross_cats_sorted":[],"title_canon_sha256":"f4cf65f5f51f81230b8fc894b6da54210ed48528bdf1f08647494e1f4ee41192","abstract_canon_sha256":"9896831c16c348fa89327deed262184523decec34a5a3187d77c121485a62121"},"schema_version":"1.0"},"canonical_sha256":"f23838d555e1b73c135bf63af636106d1ce8f31a12d890bf3e270c9045009999","source":{"kind":"arxiv","id":"1802.02615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.02615","created_at":"2026-05-18T00:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"1802.02615v1","created_at":"2026-05-18T00:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02615","created_at":"2026-05-18T00:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"6I4DRVKV4G3T","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6I4DRVKV4G3TYE23","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6I4DRVKV","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6I4DRVKV4G3TYE236Y5PMNQQNU","target":"record","payload":{"canonical_record":{"source":{"id":"1802.02615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-07T19:43:01Z","cross_cats_sorted":[],"title_canon_sha256":"f4cf65f5f51f81230b8fc894b6da54210ed48528bdf1f08647494e1f4ee41192","abstract_canon_sha256":"9896831c16c348fa89327deed262184523decec34a5a3187d77c121485a62121"},"schema_version":"1.0"},"canonical_sha256":"f23838d555e1b73c135bf63af636106d1ce8f31a12d890bf3e270c9045009999","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:03.550021Z","signature_b64":"D+zKT2f5BujWci471rtRLwOiVyBA6c+l04ilUfBm++pPqHmea6ZdRO9KnXM5G+572t0glSqv/TuTV6/LNxvCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f23838d555e1b73c135bf63af636106d1ce8f31a12d890bf3e270c9045009999","last_reissued_at":"2026-05-18T00:24:03.549660Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:03.549660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.02615","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":"2026-05-18T00:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/x0t3m4pgM0ZwLAP4pdCOYzvniJisyL3nim5dDMO2a7B+3xJcfESDdSxkCEAnxY5J+gLp5NCwnDW5pGFhejSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:53:57.127620Z"},"content_sha256":"72203e893c081f3040b0a73d36733541bfad7d48b6f191cd60bc2e5ce00c22c3","schema_version":"1.0","event_id":"sha256:72203e893c081f3040b0a73d36733541bfad7d48b6f191cd60bc2e5ce00c22c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6I4DRVKV4G3TYE236Y5PMNQQNU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Quantization Approaches for Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam T Moody, Brian C Van Essen, Md Zahangir Alom, Naoya Maruyama, Tarek M. Taha","submitted_at":"2018-02-07T19:43:01Z","abstract_excerpt":"Deep learning, and in particular Recurrent Neural Networks (RNN) have shown superior accuracy in a large variety of tasks including machine translation, language understanding, and movie frame generation. However, these deep learning approaches are very expensive in terms of computation. In most cases, Graphic Processing Units (GPUs) are in used for large scale implementations. Meanwhile, energy efficient RNN approaches are proposed for deploying solutions on special purpose hardware including Field Programming Gate Arrays (FPGAs) and mobile platforms. In this paper, we propose an effective qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02615","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":"2026-05-18T00:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zc8xjoHf5H84SJj0eaAYNsrkDkBV/tp7cvFJm3b57dG8u2zkfEkHthKNFeniW6yz6Er4TT3CSAevc1njgtC7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:53:57.127964Z"},"content_sha256":"7415a81353cd799c3b983b092769fe7c3937c25fc2d39a8702fc782a56e791c7","schema_version":"1.0","event_id":"sha256:7415a81353cd799c3b983b092769fe7c3937c25fc2d39a8702fc782a56e791c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6I4DRVKV4G3TYE236Y5PMNQQNU/bundle.json","state_url":"https://pith.science/pith/6I4DRVKV4G3TYE236Y5PMNQQNU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6I4DRVKV4G3TYE236Y5PMNQQNU/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":"2026-06-01T12:53:57Z","links":{"resolver":"https://pith.science/pith/6I4DRVKV4G3TYE236Y5PMNQQNU","bundle":"https://pith.science/pith/6I4DRVKV4G3TYE236Y5PMNQQNU/bundle.json","state":"https://pith.science/pith/6I4DRVKV4G3TYE236Y5PMNQQNU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6I4DRVKV4G3TYE236Y5PMNQQNU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6I4DRVKV4G3TYE236Y5PMNQQNU","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":"9896831c16c348fa89327deed262184523decec34a5a3187d77c121485a62121","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-07T19:43:01Z","title_canon_sha256":"f4cf65f5f51f81230b8fc894b6da54210ed48528bdf1f08647494e1f4ee41192"},"schema_version":"1.0","source":{"id":"1802.02615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.02615","created_at":"2026-05-18T00:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"1802.02615v1","created_at":"2026-05-18T00:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02615","created_at":"2026-05-18T00:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"6I4DRVKV4G3T","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6I4DRVKV4G3TYE23","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6I4DRVKV","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:7415a81353cd799c3b983b092769fe7c3937c25fc2d39a8702fc782a56e791c7","target":"graph","created_at":"2026-05-18T00:24:03Z","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":"Deep learning, and in particular Recurrent Neural Networks (RNN) have shown superior accuracy in a large variety of tasks including machine translation, language understanding, and movie frame generation. However, these deep learning approaches are very expensive in terms of computation. In most cases, Graphic Processing Units (GPUs) are in used for large scale implementations. Meanwhile, energy efficient RNN approaches are proposed for deploying solutions on special purpose hardware including Field Programming Gate Arrays (FPGAs) and mobile platforms. In this paper, we propose an effective qu","authors_text":"Adam T Moody, Brian C Van Essen, Md Zahangir Alom, Naoya Maruyama, Tarek M. Taha","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-07T19:43:01Z","title":"Effective Quantization Approaches for Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02615","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":"sha256:72203e893c081f3040b0a73d36733541bfad7d48b6f191cd60bc2e5ce00c22c3","target":"record","created_at":"2026-05-18T00:24:03Z","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":"9896831c16c348fa89327deed262184523decec34a5a3187d77c121485a62121","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-07T19:43:01Z","title_canon_sha256":"f4cf65f5f51f81230b8fc894b6da54210ed48528bdf1f08647494e1f4ee41192"},"schema_version":"1.0","source":{"id":"1802.02615","kind":"arxiv","version":1}},"canonical_sha256":"f23838d555e1b73c135bf63af636106d1ce8f31a12d890bf3e270c9045009999","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f23838d555e1b73c135bf63af636106d1ce8f31a12d890bf3e270c9045009999","first_computed_at":"2026-05-18T00:24:03.549660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:03.549660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D+zKT2f5BujWci471rtRLwOiVyBA6c+l04ilUfBm++pPqHmea6ZdRO9KnXM5G+572t0glSqv/TuTV6/LNxvCBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:03.550021Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.02615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72203e893c081f3040b0a73d36733541bfad7d48b6f191cd60bc2e5ce00c22c3","sha256:7415a81353cd799c3b983b092769fe7c3937c25fc2d39a8702fc782a56e791c7"],"state_sha256":"7ed5a5ac04cee318a06625f2b2da171635199024ffcc89fdd3d76356db11b2b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNIkwa6lyNM6+1neGanHdoa4QecqiSr7V1zIboqOmd5qWo4PZIzmoMmvdScuIMzEPCdnanS3lqKMRVAU/z+4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T12:53:57.129975Z","bundle_sha256":"a33a8402f8348191d0f3eb53433c4f830fb854807f8af27f61c5ca386ea87e0a"}}