{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ARC6OT6BK4NATAQPXJ336E4GAI","short_pith_number":"pith:ARC6OT6B","canonical_record":{"source":{"id":"2103.05787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T23:45:13Z","cross_cats_sorted":[],"title_canon_sha256":"79865fc3084112d2ee06dc77a3f759a81de97678d3a19546d9355e6ed77843a5","abstract_canon_sha256":"db576cf5e762e959236182a93b84375a4009989349f307ac087480e9466bc98a"},"schema_version":"1.0"},"canonical_sha256":"0445e74fc1571a09820fba77bf1386022cd9ce6f33722d4bc46390d6a70b9302","source":{"kind":"arxiv","id":"2103.05787","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.05787","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2103.05787v1","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05787","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"ARC6OT6BK4NA","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"ARC6OT6BK4NATAQP","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"ARC6OT6B","created_at":"2026-07-05T02:21:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ARC6OT6BK4NATAQPXJ336E4GAI","target":"record","payload":{"canonical_record":{"source":{"id":"2103.05787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T23:45:13Z","cross_cats_sorted":[],"title_canon_sha256":"79865fc3084112d2ee06dc77a3f759a81de97678d3a19546d9355e6ed77843a5","abstract_canon_sha256":"db576cf5e762e959236182a93b84375a4009989349f307ac087480e9466bc98a"},"schema_version":"1.0"},"canonical_sha256":"0445e74fc1571a09820fba77bf1386022cd9ce6f33722d4bc46390d6a70b9302","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:58.409851Z","signature_b64":"AldQDsXOQsODnaCEkPQg+KO3fM8TrG3MHjXjdoWdEotB4idZquYvc/fz+1Ori5aMECEeThqktBUU/hEXS7G3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0445e74fc1571a09820fba77bf1386022cd9ce6f33722d4bc46390d6a70b9302","last_reissued_at":"2026-07-05T02:21:58.409401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:58.409401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.05787","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fJ4gO3UTbYjXnViKvzncUgJT+D4ljltYtFQJCjgVhC/BpUUASAY9chCf9OeEKwuw6bcvb9acwn7qwjf6n2LACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:50:06.933642Z"},"content_sha256":"377af10bfbb05d7d4d6a720f30a4ae00cec5343e4e485480b4a4179884878431","schema_version":"1.0","event_id":"sha256:377af10bfbb05d7d4d6a720f30a4ae00cec5343e4e485480b4a4179884878431"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ARC6OT6BK4NATAQPXJ336E4GAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Online Recurrent Learning Using Columnar Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Khurram Javed, Martha White, Rich Sutton","submitted_at":"2021-03-09T23:45:13Z","abstract_excerpt":"Structural credit assignment for recurrent learning is challenging. An algorithm called RTRL can compute gradients for recurrent networks online but is computationally intractable for large networks. Alternatives, such as BPTT, are not online. In this work, we propose a credit-assignment algorithm -- \\algoname{} -- that approximates the gradients for recurrent learning in real-time using $O(n)$ operations and memory per-step. Our method builds on the idea that for modular recurrent networks, composed of columns with scalar states, it is sufficient for a parameter to only track its influence on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05787","kind":"arxiv","version":1},"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/2103.05787/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":"2026-07-05T02:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"znp6YZ3rCUAVt7Rl9VIreZ8LsxwDMPPJy8Apt6HzM0lfqFbJDd7s8ATSg+R4gfnRjwHFvhgDB2/3DGwypqcoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:50:06.934247Z"},"content_sha256":"cce84f25cdba405c81e34c0a40d34d6e748988d0a74f6643d23b08769fd48d34","schema_version":"1.0","event_id":"sha256:cce84f25cdba405c81e34c0a40d34d6e748988d0a74f6643d23b08769fd48d34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ARC6OT6BK4NATAQPXJ336E4GAI/bundle.json","state_url":"https://pith.science/pith/ARC6OT6BK4NATAQPXJ336E4GAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ARC6OT6BK4NATAQPXJ336E4GAI/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":"2026-08-06T22:50:06Z","links":{"resolver":"https://pith.science/pith/ARC6OT6BK4NATAQPXJ336E4GAI","bundle":"https://pith.science/pith/ARC6OT6BK4NATAQPXJ336E4GAI/bundle.json","state":"https://pith.science/pith/ARC6OT6BK4NATAQPXJ336E4GAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ARC6OT6BK4NATAQPXJ336E4GAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ARC6OT6BK4NATAQPXJ336E4GAI","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":"db576cf5e762e959236182a93b84375a4009989349f307ac087480e9466bc98a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T23:45:13Z","title_canon_sha256":"79865fc3084112d2ee06dc77a3f759a81de97678d3a19546d9355e6ed77843a5"},"schema_version":"1.0","source":{"id":"2103.05787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.05787","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2103.05787v1","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05787","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"ARC6OT6BK4NA","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"ARC6OT6BK4NATAQP","created_at":"2026-07-05T02:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"ARC6OT6B","created_at":"2026-07-05T02:21:58Z"}],"graph_snapshots":[{"event_id":"sha256:cce84f25cdba405c81e34c0a40d34d6e748988d0a74f6643d23b08769fd48d34","target":"graph","created_at":"2026-07-05T02:21:58Z","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/2103.05787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Structural credit assignment for recurrent learning is challenging. An algorithm called RTRL can compute gradients for recurrent networks online but is computationally intractable for large networks. Alternatives, such as BPTT, are not online. In this work, we propose a credit-assignment algorithm -- \\algoname{} -- that approximates the gradients for recurrent learning in real-time using $O(n)$ operations and memory per-step. Our method builds on the idea that for modular recurrent networks, composed of columns with scalar states, it is sufficient for a parameter to only track its influence on","authors_text":"Khurram Javed, Martha White, Rich Sutton","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T23:45:13Z","title":"Scalable Online Recurrent Learning Using Columnar Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05787","kind":"arxiv","version":1},"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":"sha256:377af10bfbb05d7d4d6a720f30a4ae00cec5343e4e485480b4a4179884878431","target":"record","created_at":"2026-07-05T02:21:58Z","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":"db576cf5e762e959236182a93b84375a4009989349f307ac087480e9466bc98a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T23:45:13Z","title_canon_sha256":"79865fc3084112d2ee06dc77a3f759a81de97678d3a19546d9355e6ed77843a5"},"schema_version":"1.0","source":{"id":"2103.05787","kind":"arxiv","version":1}},"canonical_sha256":"0445e74fc1571a09820fba77bf1386022cd9ce6f33722d4bc46390d6a70b9302","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0445e74fc1571a09820fba77bf1386022cd9ce6f33722d4bc46390d6a70b9302","first_computed_at":"2026-07-05T02:21:58.409401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:21:58.409401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AldQDsXOQsODnaCEkPQg+KO3fM8TrG3MHjXjdoWdEotB4idZquYvc/fz+1Ori5aMECEeThqktBUU/hEXS7G3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:21:58.409851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.05787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:377af10bfbb05d7d4d6a720f30a4ae00cec5343e4e485480b4a4179884878431","sha256:cce84f25cdba405c81e34c0a40d34d6e748988d0a74f6643d23b08769fd48d34"],"state_sha256":"b29d9cbddcb59223371e1feb1b810c5a1486a5209e931e7bfa1ff6b55c90893a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dDiUyxpIQUMTvSxJrHg16++jfklRdjEX1BbuXVpXt3XaCZz5B+gyV1VklOvOOZ7mFdnccRFBpL4/Cv68LXYODw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:50:06.965907Z","bundle_sha256":"feecce15f36d6f1a74a83de8dbce3bf1e0129222dff3cea66dd4667fe97b56a0"}}