{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DU6FRTFZ3I253UFSAQVZRL35YE","short_pith_number":"pith:DU6FRTFZ","canonical_record":{"source":{"id":"1611.07065","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-21T21:24:45Z","cross_cats_sorted":[],"title_canon_sha256":"45c84861c4896649c14eebd975a1a68a65c9f1055e0da59fe81e6331d02fd918","abstract_canon_sha256":"c9a91a2008416f82c2686d0fd4716085c41c0ab078790c65d94a453ae0baa4e4"},"schema_version":"1.0"},"canonical_sha256":"1d3c58ccb9da35ddd0b2042b98af7dc136a218cde8f3e1a3db850b05f1b557a6","source":{"kind":"arxiv","id":"1611.07065","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.07065","created_at":"2026-05-18T00:49:57Z"},{"alias_kind":"arxiv_version","alias_value":"1611.07065v2","created_at":"2026-05-18T00:49:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07065","created_at":"2026-05-18T00:49:57Z"},{"alias_kind":"pith_short_12","alias_value":"DU6FRTFZ3I25","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DU6FRTFZ3I253UFS","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DU6FRTFZ","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DU6FRTFZ3I253UFSAQVZRL35YE","target":"record","payload":{"canonical_record":{"source":{"id":"1611.07065","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-21T21:24:45Z","cross_cats_sorted":[],"title_canon_sha256":"45c84861c4896649c14eebd975a1a68a65c9f1055e0da59fe81e6331d02fd918","abstract_canon_sha256":"c9a91a2008416f82c2686d0fd4716085c41c0ab078790c65d94a453ae0baa4e4"},"schema_version":"1.0"},"canonical_sha256":"1d3c58ccb9da35ddd0b2042b98af7dc136a218cde8f3e1a3db850b05f1b557a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:57.930139Z","signature_b64":"b9oBI+at614VogNr2S8DfA1nklZEYDshIqLs8Mmfcu2W+VKAf0dRvTrdvC5p76GCkoGZhDRTOx9svW8hxQjMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d3c58ccb9da35ddd0b2042b98af7dc136a218cde8f3e1a3db850b05f1b557a6","last_reissued_at":"2026-05-18T00:49:57.929580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:57.929580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.07065","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":"2026-05-18T00:49:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTKjWbD3R/BNwm3Ml/YclovRVD9VxHQBOV5dBSvxsP59b7NxnDy1GC9bpdOwsK+KtdVO/uVgM+SER63L/RT0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:49:18.903726Z"},"content_sha256":"1b73af16980589f453a68587ef9e8d1dc0742b220af33d652855ff7c6fc0023e","schema_version":"1.0","event_id":"sha256:1b73af16980589f453a68587ef9e8d1dc0742b220af33d652855ff7c6fc0023e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DU6FRTFZ3I253UFSAQVZRL35YE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Neural Networks With Limited Numerical Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Joachim Ott, Shih-Chii Liu, Ying Zhang, Yoshua Bengio, Zhouhan Lin","submitted_at":"2016-11-21T21:24:45Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the computations performed with these models especially when considering development of specialized low-power hardware for deep networks. One way of reducing the computational needs is to limit the numerical precision of the network weights and biases, and this will be addressed for the case of RNNs. We present results from the use of different stochastic and d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07065","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":"2026-05-18T00:49:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QdQWNCBmpdop0SPHEtMDP6oTY1dXry+qUyJr2FM2s21xFYoYZ9SOyux8/7ScWyKr3ScXW48+Gu2JkWZ4cexLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:49:18.904096Z"},"content_sha256":"9d1b39633c2800aa2bd0e07e3e1d4e9d21279a3bd223facc8d520ad92ed29914","schema_version":"1.0","event_id":"sha256:9d1b39633c2800aa2bd0e07e3e1d4e9d21279a3bd223facc8d520ad92ed29914"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DU6FRTFZ3I253UFSAQVZRL35YE/bundle.json","state_url":"https://pith.science/pith/DU6FRTFZ3I253UFSAQVZRL35YE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DU6FRTFZ3I253UFSAQVZRL35YE/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":"2026-05-30T12:49:18Z","links":{"resolver":"https://pith.science/pith/DU6FRTFZ3I253UFSAQVZRL35YE","bundle":"https://pith.science/pith/DU6FRTFZ3I253UFSAQVZRL35YE/bundle.json","state":"https://pith.science/pith/DU6FRTFZ3I253UFSAQVZRL35YE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DU6FRTFZ3I253UFSAQVZRL35YE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DU6FRTFZ3I253UFSAQVZRL35YE","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":"c9a91a2008416f82c2686d0fd4716085c41c0ab078790c65d94a453ae0baa4e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-21T21:24:45Z","title_canon_sha256":"45c84861c4896649c14eebd975a1a68a65c9f1055e0da59fe81e6331d02fd918"},"schema_version":"1.0","source":{"id":"1611.07065","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.07065","created_at":"2026-05-18T00:49:57Z"},{"alias_kind":"arxiv_version","alias_value":"1611.07065v2","created_at":"2026-05-18T00:49:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07065","created_at":"2026-05-18T00:49:57Z"},{"alias_kind":"pith_short_12","alias_value":"DU6FRTFZ3I25","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DU6FRTFZ3I253UFS","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DU6FRTFZ","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:9d1b39633c2800aa2bd0e07e3e1d4e9d21279a3bd223facc8d520ad92ed29914","target":"graph","created_at":"2026-05-18T00:49:57Z","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) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the computations performed with these models especially when considering development of specialized low-power hardware for deep networks. One way of reducing the computational needs is to limit the numerical precision of the network weights and biases, and this will be addressed for the case of RNNs. We present results from the use of different stochastic and d","authors_text":"Joachim Ott, Shih-Chii Liu, Ying Zhang, Yoshua Bengio, Zhouhan Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-21T21:24:45Z","title":"Recurrent Neural Networks With Limited Numerical Precision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07065","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":"sha256:1b73af16980589f453a68587ef9e8d1dc0742b220af33d652855ff7c6fc0023e","target":"record","created_at":"2026-05-18T00:49:57Z","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":"c9a91a2008416f82c2686d0fd4716085c41c0ab078790c65d94a453ae0baa4e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-21T21:24:45Z","title_canon_sha256":"45c84861c4896649c14eebd975a1a68a65c9f1055e0da59fe81e6331d02fd918"},"schema_version":"1.0","source":{"id":"1611.07065","kind":"arxiv","version":2}},"canonical_sha256":"1d3c58ccb9da35ddd0b2042b98af7dc136a218cde8f3e1a3db850b05f1b557a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d3c58ccb9da35ddd0b2042b98af7dc136a218cde8f3e1a3db850b05f1b557a6","first_computed_at":"2026-05-18T00:49:57.929580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:57.929580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b9oBI+at614VogNr2S8DfA1nklZEYDshIqLs8Mmfcu2W+VKAf0dRvTrdvC5p76GCkoGZhDRTOx9svW8hxQjMBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:57.930139Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.07065","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b73af16980589f453a68587ef9e8d1dc0742b220af33d652855ff7c6fc0023e","sha256:9d1b39633c2800aa2bd0e07e3e1d4e9d21279a3bd223facc8d520ad92ed29914"],"state_sha256":"8443e2b1f991847df0b22aec373ec86f3b670aff70eb58ab120d924e9d38f954"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGCu5o7E4w9cmT6IDg/zZzODlrIAPfLzStlVxl2208XrCJ+Tnmp0GRV6+hFx3wwTHHxS5Qu6KzkHzTx1Frv8Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:49:18.906524Z","bundle_sha256":"61ccf667b78831e66fe43f1cf0bba1808a380c8101caa5ab7871509fda310b81"}}