{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:F2S3F3ITYPYCGMXTPRAXOE2CVN","short_pith_number":"pith:F2S3F3IT","canonical_record":{"source":{"id":"1512.01322","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T06:07:28Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"d3427a3634c27ec8d6d0649ed3ce82e09204c9f6adb772f8a061c1f3af6c0bd5","abstract_canon_sha256":"e5e3daf1e743737553ab3fbc0517d5c24e0f41cc3cbcac47bd1913497bc368d2"},"schema_version":"1.0"},"canonical_sha256":"2ea5b2ed13c3f02332f37c41771342ab6080e6325976ed98d07ddd40ae390f7f","source":{"kind":"arxiv","id":"1512.01322","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01322","created_at":"2026-05-18T01:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01322v3","created_at":"2026-05-18T01:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01322","created_at":"2026-05-18T01:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"F2S3F3ITYPYC","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"F2S3F3ITYPYCGMXT","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"F2S3F3IT","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:F2S3F3ITYPYCGMXTPRAXOE2CVN","target":"record","payload":{"canonical_record":{"source":{"id":"1512.01322","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T06:07:28Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"d3427a3634c27ec8d6d0649ed3ce82e09204c9f6adb772f8a061c1f3af6c0bd5","abstract_canon_sha256":"e5e3daf1e743737553ab3fbc0517d5c24e0f41cc3cbcac47bd1913497bc368d2"},"schema_version":"1.0"},"canonical_sha256":"2ea5b2ed13c3f02332f37c41771342ab6080e6325976ed98d07ddd40ae390f7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:50.814987Z","signature_b64":"eu3XSuyVpeBZsHNFn0VptbVnsk5fgHMlBiQYR0pNHkojC2nCMhldn3/r0WE4gevnOhZpjuPV/D7l5mZvYGD/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ea5b2ed13c3f02332f37c41771342ab6080e6325976ed98d07ddd40ae390f7f","last_reissued_at":"2026-05-18T01:03:50.814309Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:50.814309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.01322","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WUgunNzThXenjNh518AgJKAmuNcYXg4Vi2uosLkVwTfF6J8D4tja6QvB8AuYzxCZnihVc6/BoW0konau7Eb+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:40:52.892702Z"},"content_sha256":"0c784b30b4cb2a70afd3f180864ab8689cea4f89ffcb47a32401a4489e52a5b6","schema_version":"1.0","event_id":"sha256:0c784b30b4cb2a70afd3f180864ab8689cea4f89ffcb47a32401a4489e52a5b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:F2S3F3ITYPYCGMXTPRAXOE2CVN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fixed-Point Performance Analysis of Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Kyuyeon Hwang, Sungho Shin, Wonyong Sung","submitted_at":"2015-12-04T06:07:28Z","abstract_excerpt":"Recurrent neural networks have shown excellent performance in many applications, however they require increased complexity in hardware or software based implementations. The hardware complexity can be much lowered by minimizing the word-length of weights and signals. This work analyzes the fixed-point performance of recurrent neural networks using a retrain based quantization method. The quantization sensitivity of each layer in RNNs is studied, and the overall fixed-point optimization results minimizing the capacity of weights while not sacrificing the performance are presented. A language mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01322","kind":"arxiv","version":3},"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":"2026-05-18T01:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/nf9ituCw+OzqudPRgvbIAEcoyPjqCuGrMMTPjFUDJUlIJe0Wj/GiMCazBl3ZtnUthJEYKRFBVNlbSFNzyH0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:40:52.893382Z"},"content_sha256":"38c750f57776f3c5ea17d2f16413da5ff399915c1178a02835178b72376f50da","schema_version":"1.0","event_id":"sha256:38c750f57776f3c5ea17d2f16413da5ff399915c1178a02835178b72376f50da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F2S3F3ITYPYCGMXTPRAXOE2CVN/bundle.json","state_url":"https://pith.science/pith/F2S3F3ITYPYCGMXTPRAXOE2CVN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F2S3F3ITYPYCGMXTPRAXOE2CVN/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":"2026-06-11T22:40:52Z","links":{"resolver":"https://pith.science/pith/F2S3F3ITYPYCGMXTPRAXOE2CVN","bundle":"https://pith.science/pith/F2S3F3ITYPYCGMXTPRAXOE2CVN/bundle.json","state":"https://pith.science/pith/F2S3F3ITYPYCGMXTPRAXOE2CVN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F2S3F3ITYPYCGMXTPRAXOE2CVN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:F2S3F3ITYPYCGMXTPRAXOE2CVN","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":"e5e3daf1e743737553ab3fbc0517d5c24e0f41cc3cbcac47bd1913497bc368d2","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T06:07:28Z","title_canon_sha256":"d3427a3634c27ec8d6d0649ed3ce82e09204c9f6adb772f8a061c1f3af6c0bd5"},"schema_version":"1.0","source":{"id":"1512.01322","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01322","created_at":"2026-05-18T01:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01322v3","created_at":"2026-05-18T01:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01322","created_at":"2026-05-18T01:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"F2S3F3ITYPYC","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"F2S3F3ITYPYCGMXT","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"F2S3F3IT","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:38c750f57776f3c5ea17d2f16413da5ff399915c1178a02835178b72376f50da","target":"graph","created_at":"2026-05-18T01:03:50Z","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 have shown excellent performance in many applications, however they require increased complexity in hardware or software based implementations. The hardware complexity can be much lowered by minimizing the word-length of weights and signals. This work analyzes the fixed-point performance of recurrent neural networks using a retrain based quantization method. The quantization sensitivity of each layer in RNNs is studied, and the overall fixed-point optimization results minimizing the capacity of weights while not sacrificing the performance are presented. A language mo","authors_text":"Kyuyeon Hwang, Sungho Shin, Wonyong Sung","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T06:07:28Z","title":"Fixed-Point Performance Analysis of Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01322","kind":"arxiv","version":3},"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":"sha256:0c784b30b4cb2a70afd3f180864ab8689cea4f89ffcb47a32401a4489e52a5b6","target":"record","created_at":"2026-05-18T01:03:50Z","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":"e5e3daf1e743737553ab3fbc0517d5c24e0f41cc3cbcac47bd1913497bc368d2","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T06:07:28Z","title_canon_sha256":"d3427a3634c27ec8d6d0649ed3ce82e09204c9f6adb772f8a061c1f3af6c0bd5"},"schema_version":"1.0","source":{"id":"1512.01322","kind":"arxiv","version":3}},"canonical_sha256":"2ea5b2ed13c3f02332f37c41771342ab6080e6325976ed98d07ddd40ae390f7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ea5b2ed13c3f02332f37c41771342ab6080e6325976ed98d07ddd40ae390f7f","first_computed_at":"2026-05-18T01:03:50.814309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:50.814309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eu3XSuyVpeBZsHNFn0VptbVnsk5fgHMlBiQYR0pNHkojC2nCMhldn3/r0WE4gevnOhZpjuPV/D7l5mZvYGD/Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:50.814987Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.01322","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c784b30b4cb2a70afd3f180864ab8689cea4f89ffcb47a32401a4489e52a5b6","sha256:38c750f57776f3c5ea17d2f16413da5ff399915c1178a02835178b72376f50da"],"state_sha256":"f6bbee413e71dd7cf8565c0f76848f50d40f0513db05d07347e63cec6198b777"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14VpBZU59snQKiZ5OGphpJ6e+MgE9gHyPkOxhghYO/g0FCdMjRYnUKWVxoVuHzzJAmNLWexAhNsgEM4dGIdODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T22:40:52.896921Z","bundle_sha256":"96e1c3a4b2892f65d1e1f12297cc918dc297d101884d2230ee43dc991fdf8812"}}