{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:TBIMU3IVIESWVMW2OI3ZCURMFF","short_pith_number":"pith:TBIMU3IV","canonical_record":{"source":{"id":"1511.01169","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T00:38:03Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"cc639500517bbd528b99b21015863fe56f531360a317dd500742a0c436552d13","abstract_canon_sha256":"3d069913c4824540bfe8da7d94db6cf40330a1b3fa32e414422db9ed8a049db3"},"schema_version":"1.0"},"canonical_sha256":"9850ca6d1541256ab2da723791522c296eed44ebb9e8d494571c3a15708c6c53","source":{"kind":"arxiv","id":"1511.01169","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.01169","created_at":"2026-05-18T01:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"1511.01169v5","created_at":"2026-05-18T01:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01169","created_at":"2026-05-18T01:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"TBIMU3IVIESW","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"TBIMU3IVIESWVMW2","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"TBIMU3IV","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:TBIMU3IVIESWVMW2OI3ZCURMFF","target":"record","payload":{"canonical_record":{"source":{"id":"1511.01169","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T00:38:03Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"cc639500517bbd528b99b21015863fe56f531360a317dd500742a0c436552d13","abstract_canon_sha256":"3d069913c4824540bfe8da7d94db6cf40330a1b3fa32e414422db9ed8a049db3"},"schema_version":"1.0"},"canonical_sha256":"9850ca6d1541256ab2da723791522c296eed44ebb9e8d494571c3a15708c6c53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:06.385788Z","signature_b64":"YM/OQETYjR192O2+MmE8OZvFIVLmSfngAS1uqTT2vdCgTHv0ALFTI8v15j2hSvHNYEPGa0RW8CzQYQtOO9ymDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9850ca6d1541256ab2da723791522c296eed44ebb9e8d494571c3a15708c6c53","last_reissued_at":"2026-05-18T01:20:06.385066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:06.385066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.01169","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:20:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v7XBOJsES4Dumixk3bJVHKNUY6Oby/bndV+lo62cwujoT8CTmsdIQ7eXvSnTC1Uxa002wBCCWKvAQ415ADijAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:05:54.164915Z"},"content_sha256":"e7e047fbadbabe30ef40d09152abdfa9657c371e57643dd046cdca0f9adc375d","schema_version":"1.0","event_id":"sha256:e7e047fbadbabe30ef40d09152abdfa9657c371e57643dd046cdca0f9adc375d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:TBIMU3IVIESWVMW2OI3ZCURMFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"adaQN: An Adaptive Quasi-Newton Algorithm for Training RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Albert S. Berahas, Nitish Shirish Keskar","submitted_at":"2015-11-04T00:38:03Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are powerful models that achieve exceptional performance on several pattern recognition problems. However, the training of RNNs is a computationally difficult task owing to the well-known \"vanishing/exploding\" gradient problem. Algorithms proposed for training RNNs either exploit no (or limited) curvature information and have cheap per-iteration complexity, or attempt to gain significant curvature information at the cost of increased per-iteration cost. The former set includes diagonally-scaled first-order methods such as ADAGRAD and ADAM, while the latter cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.01169","kind":"arxiv","version":5},"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":"2026-05-18T01:20:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WPvseDykqeAfmxODkKVT5yvhfHxYBu76F3qkVP5q+s9uOnF6T9HPwy9DuChD8R9jp++uHkkwGuMXBkbsgXSIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:05:54.165615Z"},"content_sha256":"84ee4a654c7f29b70ccee98a4554c63ce3131a93042301060d43f0fd19c22e6e","schema_version":"1.0","event_id":"sha256:84ee4a654c7f29b70ccee98a4554c63ce3131a93042301060d43f0fd19c22e6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/bundle.json","state_url":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/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":"2026-06-05T04:05:54Z","links":{"resolver":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF","bundle":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/bundle.json","state":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:TBIMU3IVIESWVMW2OI3ZCURMFF","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":"3d069913c4824540bfe8da7d94db6cf40330a1b3fa32e414422db9ed8a049db3","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T00:38:03Z","title_canon_sha256":"cc639500517bbd528b99b21015863fe56f531360a317dd500742a0c436552d13"},"schema_version":"1.0","source":{"id":"1511.01169","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.01169","created_at":"2026-05-18T01:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"1511.01169v5","created_at":"2026-05-18T01:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01169","created_at":"2026-05-18T01:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"TBIMU3IVIESW","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"TBIMU3IVIESWVMW2","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"TBIMU3IV","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:84ee4a654c7f29b70ccee98a4554c63ce3131a93042301060d43f0fd19c22e6e","target":"graph","created_at":"2026-05-18T01:20:06Z","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) are powerful models that achieve exceptional performance on several pattern recognition problems. However, the training of RNNs is a computationally difficult task owing to the well-known \"vanishing/exploding\" gradient problem. Algorithms proposed for training RNNs either exploit no (or limited) curvature information and have cheap per-iteration complexity, or attempt to gain significant curvature information at the cost of increased per-iteration cost. The former set includes diagonally-scaled first-order methods such as ADAGRAD and ADAM, while the latter cons","authors_text":"Albert S. Berahas, Nitish Shirish Keskar","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T00:38:03Z","title":"adaQN: An Adaptive Quasi-Newton Algorithm for Training RNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.01169","kind":"arxiv","version":5},"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:e7e047fbadbabe30ef40d09152abdfa9657c371e57643dd046cdca0f9adc375d","target":"record","created_at":"2026-05-18T01:20:06Z","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":"3d069913c4824540bfe8da7d94db6cf40330a1b3fa32e414422db9ed8a049db3","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T00:38:03Z","title_canon_sha256":"cc639500517bbd528b99b21015863fe56f531360a317dd500742a0c436552d13"},"schema_version":"1.0","source":{"id":"1511.01169","kind":"arxiv","version":5}},"canonical_sha256":"9850ca6d1541256ab2da723791522c296eed44ebb9e8d494571c3a15708c6c53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9850ca6d1541256ab2da723791522c296eed44ebb9e8d494571c3a15708c6c53","first_computed_at":"2026-05-18T01:20:06.385066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:06.385066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YM/OQETYjR192O2+MmE8OZvFIVLmSfngAS1uqTT2vdCgTHv0ALFTI8v15j2hSvHNYEPGa0RW8CzQYQtOO9ymDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:06.385788Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.01169","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7e047fbadbabe30ef40d09152abdfa9657c371e57643dd046cdca0f9adc375d","sha256:84ee4a654c7f29b70ccee98a4554c63ce3131a93042301060d43f0fd19c22e6e"],"state_sha256":"8a4437ab18e3b6b62b8532ac2ebca4f059dea3c63e8fcf8ab84d95a26c3cc382"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LUmHirx7zQy0sE1pTH6/oCy4vVEbUHxhIN7iP0AAfUhFa20qCm8SS8N/6IdaRkJXeCwEqTtBkOMmGyjHrJcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T04:05:54.169326Z","bundle_sha256":"774a88481a7b61d33f7260d265db6bf16d4c6ec42e35217cf5f5331449e79d92"}}