{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:56GSEI4LZI224CAKFQA5FTWCQG","short_pith_number":"pith:56GSEI4L","canonical_record":{"source":{"id":"2305.19044","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T13:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"ca543f05951b1ca35bd73ab1057b2e67a3c88b3f3515141c269ec9c4dcf2b1e3","abstract_canon_sha256":"fe0bd79572c7fc184715ca6509459fe55d0c09c4783f1563c97b82ea5d7720de"},"schema_version":"1.0"},"canonical_sha256":"ef8d22238bca35ae080a2c01d2cec281b36c912eb2b696dc337445e0478c0a0d","source":{"kind":"arxiv","id":"2305.19044","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19044","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19044v3","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19044","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"pith_short_12","alias_value":"56GSEI4LZI22","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"pith_short_16","alias_value":"56GSEI4LZI224CAK","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"pith_short_8","alias_value":"56GSEI4L","created_at":"2026-07-05T07:50:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:56GSEI4LZI224CAKFQA5FTWCQG","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19044","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T13:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"ca543f05951b1ca35bd73ab1057b2e67a3c88b3f3515141c269ec9c4dcf2b1e3","abstract_canon_sha256":"fe0bd79572c7fc184715ca6509459fe55d0c09c4783f1563c97b82ea5d7720de"},"schema_version":"1.0"},"canonical_sha256":"ef8d22238bca35ae080a2c01d2cec281b36c912eb2b696dc337445e0478c0a0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:01.726377Z","signature_b64":"sEysWd9CXT3u2DNYRJ0fW19+Cj3wz/51ZoXCyQwNVPfxYO2e4UL1U3C5NT+qM1bz0dY8iUhopEObdzjbasKUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef8d22238bca35ae080a2c01d2cec281b36c912eb2b696dc337445e0478c0a0d","last_reissued_at":"2026-07-05T07:50:01.725786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:01.725786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19044","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":"2026-07-05T07:50:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4POgrOnS4Sr0HaNDrysbm5fvBTg2+o4hy2ElZ9Dg8GXEwVDTo6OfyhDaPJ0yKanQj3/5RV8h/vTG2NwuOrgYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:59:35.628857Z"},"content_sha256":"585a0855b8395d60ffd39b74e2b96632062d90689b905544572c514bd3b25598","schema_version":"1.0","event_id":"sha256:585a0855b8395d60ffd39b74e2b96632062d90689b905544572c514bd3b25598"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:56GSEI4LZI224CAKFQA5FTWCQG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anand Gopalakrishnan, J\\\"urgen Schmidhuber, Kazuki Irie","submitted_at":"2023-05-30T13:59:21Z","abstract_excerpt":"Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks (RNNs) offers certain conceptual advantages over backpropagation through time (BPTT). RTRL requires neither caching past activations nor truncating context, and enables online learning. However, RTRL's time and space complexity make it impractical. To overcome this problem, most recent work on RTRL focuses on approximation theories, while experiments are often limited to diagnostic settings. Here we explore the practical promise of RTRL in more realistic settings. We study actor-critic methods that combine RT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19044","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.19044/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T07:50:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ubxykwgpb71EjXfmOSOmWnRDAqOnVqhpSDJ9umKLJ0s+F/hSKmuGPc4/Gmm2MhVjF4P5JiKlP2doYzTvhKkWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:59:35.629928Z"},"content_sha256":"4a3495123edc9543e4ac7c9188203027f200c423284ce328644d6a863e860041","schema_version":"1.0","event_id":"sha256:4a3495123edc9543e4ac7c9188203027f200c423284ce328644d6a863e860041"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/56GSEI4LZI224CAKFQA5FTWCQG/bundle.json","state_url":"https://pith.science/pith/56GSEI4LZI224CAKFQA5FTWCQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/56GSEI4LZI224CAKFQA5FTWCQG/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":"2026-08-14T01:59:35Z","links":{"resolver":"https://pith.science/pith/56GSEI4LZI224CAKFQA5FTWCQG","bundle":"https://pith.science/pith/56GSEI4LZI224CAKFQA5FTWCQG/bundle.json","state":"https://pith.science/pith/56GSEI4LZI224CAKFQA5FTWCQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/56GSEI4LZI224CAKFQA5FTWCQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:56GSEI4LZI224CAKFQA5FTWCQG","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":"fe0bd79572c7fc184715ca6509459fe55d0c09c4783f1563c97b82ea5d7720de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T13:59:21Z","title_canon_sha256":"ca543f05951b1ca35bd73ab1057b2e67a3c88b3f3515141c269ec9c4dcf2b1e3"},"schema_version":"1.0","source":{"id":"2305.19044","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19044","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19044v3","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19044","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"pith_short_12","alias_value":"56GSEI4LZI22","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"pith_short_16","alias_value":"56GSEI4LZI224CAK","created_at":"2026-07-05T07:50:01Z"},{"alias_kind":"pith_short_8","alias_value":"56GSEI4L","created_at":"2026-07-05T07:50:01Z"}],"graph_snapshots":[{"event_id":"sha256:4a3495123edc9543e4ac7c9188203027f200c423284ce328644d6a863e860041","target":"graph","created_at":"2026-07-05T07:50:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.19044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks (RNNs) offers certain conceptual advantages over backpropagation through time (BPTT). RTRL requires neither caching past activations nor truncating context, and enables online learning. However, RTRL's time and space complexity make it impractical. To overcome this problem, most recent work on RTRL focuses on approximation theories, while experiments are often limited to diagnostic settings. Here we explore the practical promise of RTRL in more realistic settings. We study actor-critic methods that combine RT","authors_text":"Anand Gopalakrishnan, J\\\"urgen Schmidhuber, Kazuki Irie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T13:59:21Z","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19044","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":"sha256:585a0855b8395d60ffd39b74e2b96632062d90689b905544572c514bd3b25598","target":"record","created_at":"2026-07-05T07:50:01Z","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":"fe0bd79572c7fc184715ca6509459fe55d0c09c4783f1563c97b82ea5d7720de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T13:59:21Z","title_canon_sha256":"ca543f05951b1ca35bd73ab1057b2e67a3c88b3f3515141c269ec9c4dcf2b1e3"},"schema_version":"1.0","source":{"id":"2305.19044","kind":"arxiv","version":3}},"canonical_sha256":"ef8d22238bca35ae080a2c01d2cec281b36c912eb2b696dc337445e0478c0a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef8d22238bca35ae080a2c01d2cec281b36c912eb2b696dc337445e0478c0a0d","first_computed_at":"2026-07-05T07:50:01.725786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:01.725786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sEysWd9CXT3u2DNYRJ0fW19+Cj3wz/51ZoXCyQwNVPfxYO2e4UL1U3C5NT+qM1bz0dY8iUhopEObdzjbasKUBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:01.726377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19044","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:585a0855b8395d60ffd39b74e2b96632062d90689b905544572c514bd3b25598","sha256:4a3495123edc9543e4ac7c9188203027f200c423284ce328644d6a863e860041"],"state_sha256":"eb8c56acc9de23e0963b9f2082f53113e4e9205522981f65bc5b29f502eb51c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IieUlmGPaVQnBL+b9Y9UZzJaw0btzt5yHZqKMqnUBG7lWRmFmBmS2f1Zmtj+gKMNQr51ZB3RNmI5ru3M8CDDDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T01:59:35.724569Z","bundle_sha256":"f39bb5e014e031d68b1c67f79bac6867e545047b027c6285d805e903beca6ef1"}}