{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:JY4SI7Q6T7QG4GHPEII447XM2E","short_pith_number":"pith:JY4SI7Q6","canonical_record":{"source":{"id":"1611.01576","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T00:31:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7f29f9e78fb6739e3ea025913ee0ab4fde2089acfd49ab0f175bfd9a7b395f6e","abstract_canon_sha256":"cbdb8842bdaa394272f57cc6da3d6b8359bdfce5ce1c0f5b22acafbd5964f015"},"schema_version":"1.0"},"canonical_sha256":"4e39247e1e9fe06e18ef2211ce7eecd1349d251e258a02126e14be42a688a3df","source":{"kind":"arxiv","id":"1611.01576","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01576","created_at":"2026-05-18T00:57:37Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01576v2","created_at":"2026-05-18T00:57:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01576","created_at":"2026-05-18T00:57:37Z"},{"alias_kind":"pith_short_12","alias_value":"JY4SI7Q6T7QG","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JY4SI7Q6T7QG4GHP","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JY4SI7Q6","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:JY4SI7Q6T7QG4GHPEII447XM2E","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01576","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T00:31:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7f29f9e78fb6739e3ea025913ee0ab4fde2089acfd49ab0f175bfd9a7b395f6e","abstract_canon_sha256":"cbdb8842bdaa394272f57cc6da3d6b8359bdfce5ce1c0f5b22acafbd5964f015"},"schema_version":"1.0"},"canonical_sha256":"4e39247e1e9fe06e18ef2211ce7eecd1349d251e258a02126e14be42a688a3df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:37.114201Z","signature_b64":"N45GNaXc7Tr6yBXgKBkysSBzq6Go6MbitvEgW0b2+Z37bLo0H9L3N25tscRLt2UEoAhnDne6HUrAtSC0pJHrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e39247e1e9fe06e18ef2211ce7eecd1349d251e258a02126e14be42a688a3df","last_reissued_at":"2026-05-18T00:57:37.113602Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:37.113602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01576","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":"2026-05-18T00:57:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p1sBIiJQYEz93zPWcWwLYhcTixjYoKngFodHK9R2VFO6tSvkZY9zkhabbvbuyfFc7pJu2cba5LYHrmztMsMcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:10:16.796439Z"},"content_sha256":"ca184d76b8aff80d10269228076eadb389b4d59194e38adac73f2c4000752d53","schema_version":"1.0","event_id":"sha256:ca184d76b8aff80d10269228076eadb389b4d59194e38adac73f2c4000752d53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:JY4SI7Q6T7QG4GHPEII447XM2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quasi-Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.NE","authors_text":"Caiming Xiong, James Bradbury, Richard Socher, Stephen Merity","submitted_at":"2016-11-05T00:31:25Z","abstract_excerpt":"Recurrent neural networks are a powerful tool for modeling sequential data, but the dependence of each timestep's computation on the previous timestep's output limits parallelism and makes RNNs unwieldy for very long sequences. We introduce quasi-recurrent neural networks (QRNNs), an approach to neural sequence modeling that alternates convolutional layers, which apply in parallel across timesteps, and a minimalist recurrent pooling function that applies in parallel across channels. Despite lacking trainable recurrent layers, stacked QRNNs have better predictive accuracy than stacked LSTMs of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01576","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":"2026-05-18T00:57:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vjwKbUfTHBsWVGyc1UthrJ00NODAK+YYku/E6lI8y+OBKI6vsdOZlOIz8VfzgZi4jo69DhH+/b/g7yNNbh2ICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:10:16.797123Z"},"content_sha256":"751431034ade14ddebcabe77fc8c18c71cd03a67cf64dd53ccccd7f158d34d80","schema_version":"1.0","event_id":"sha256:751431034ade14ddebcabe77fc8c18c71cd03a67cf64dd53ccccd7f158d34d80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JY4SI7Q6T7QG4GHPEII447XM2E/bundle.json","state_url":"https://pith.science/pith/JY4SI7Q6T7QG4GHPEII447XM2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JY4SI7Q6T7QG4GHPEII447XM2E/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":"2026-05-27T16:10:16Z","links":{"resolver":"https://pith.science/pith/JY4SI7Q6T7QG4GHPEII447XM2E","bundle":"https://pith.science/pith/JY4SI7Q6T7QG4GHPEII447XM2E/bundle.json","state":"https://pith.science/pith/JY4SI7Q6T7QG4GHPEII447XM2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JY4SI7Q6T7QG4GHPEII447XM2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:JY4SI7Q6T7QG4GHPEII447XM2E","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":"cbdb8842bdaa394272f57cc6da3d6b8359bdfce5ce1c0f5b22acafbd5964f015","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T00:31:25Z","title_canon_sha256":"7f29f9e78fb6739e3ea025913ee0ab4fde2089acfd49ab0f175bfd9a7b395f6e"},"schema_version":"1.0","source":{"id":"1611.01576","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01576","created_at":"2026-05-18T00:57:37Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01576v2","created_at":"2026-05-18T00:57:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01576","created_at":"2026-05-18T00:57:37Z"},{"alias_kind":"pith_short_12","alias_value":"JY4SI7Q6T7QG","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JY4SI7Q6T7QG4GHP","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JY4SI7Q6","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:751431034ade14ddebcabe77fc8c18c71cd03a67cf64dd53ccccd7f158d34d80","target":"graph","created_at":"2026-05-18T00:57:37Z","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 are a powerful tool for modeling sequential data, but the dependence of each timestep's computation on the previous timestep's output limits parallelism and makes RNNs unwieldy for very long sequences. We introduce quasi-recurrent neural networks (QRNNs), an approach to neural sequence modeling that alternates convolutional layers, which apply in parallel across timesteps, and a minimalist recurrent pooling function that applies in parallel across channels. Despite lacking trainable recurrent layers, stacked QRNNs have better predictive accuracy than stacked LSTMs of ","authors_text":"Caiming Xiong, James Bradbury, Richard Socher, Stephen Merity","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T00:31:25Z","title":"Quasi-Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01576","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:ca184d76b8aff80d10269228076eadb389b4d59194e38adac73f2c4000752d53","target":"record","created_at":"2026-05-18T00:57:37Z","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":"cbdb8842bdaa394272f57cc6da3d6b8359bdfce5ce1c0f5b22acafbd5964f015","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T00:31:25Z","title_canon_sha256":"7f29f9e78fb6739e3ea025913ee0ab4fde2089acfd49ab0f175bfd9a7b395f6e"},"schema_version":"1.0","source":{"id":"1611.01576","kind":"arxiv","version":2}},"canonical_sha256":"4e39247e1e9fe06e18ef2211ce7eecd1349d251e258a02126e14be42a688a3df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e39247e1e9fe06e18ef2211ce7eecd1349d251e258a02126e14be42a688a3df","first_computed_at":"2026-05-18T00:57:37.113602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:57:37.113602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N45GNaXc7Tr6yBXgKBkysSBzq6Go6MbitvEgW0b2+Z37bLo0H9L3N25tscRLt2UEoAhnDne6HUrAtSC0pJHrDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:57:37.114201Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01576","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca184d76b8aff80d10269228076eadb389b4d59194e38adac73f2c4000752d53","sha256:751431034ade14ddebcabe77fc8c18c71cd03a67cf64dd53ccccd7f158d34d80"],"state_sha256":"213cd4d92cb159dc031540b898e1c6ad5a6ea352c7c1a31b76a8f9be85acb66d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R3PcMV0ePUL2AIR7mdzrVJnTE2nVt8QUt5Br4ejeTMW1HH9T4aYkkjSx7vuND7neNmmmLoQTBHYTGWVX7UZRDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T16:10:16.800536Z","bundle_sha256":"a179aedc6984104a4da28578b9d78dc5d7461f51f5d68a8ee143140739368fb7"}}