{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZCF3UXQAV2BUOILFDSCZW6KNBD","short_pith_number":"pith:ZCF3UXQA","canonical_record":{"source":{"id":"2310.13284","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T05:30:30Z","cross_cats_sorted":[],"title_canon_sha256":"502dd241cc74f11dfa48bbe6162d2a956432a978c96af25d051f727970cabccb","abstract_canon_sha256":"0a2706a0bdf3a400eff1c694947131a52990f173ef676841d88eda359cad0d7f"},"schema_version":"1.0"},"canonical_sha256":"c88bba5e00ae834721651c859b794d08e783109aa86a536432398ae2fc78d125","source":{"kind":"arxiv","id":"2310.13284","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13284","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13284v1","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13284","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZCF3UXQAV2BU","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZCF3UXQAV2BUOILF","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZCF3UXQA","created_at":"2026-07-05T07:03:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZCF3UXQAV2BUOILFDSCZW6KNBD","target":"record","payload":{"canonical_record":{"source":{"id":"2310.13284","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T05:30:30Z","cross_cats_sorted":[],"title_canon_sha256":"502dd241cc74f11dfa48bbe6162d2a956432a978c96af25d051f727970cabccb","abstract_canon_sha256":"0a2706a0bdf3a400eff1c694947131a52990f173ef676841d88eda359cad0d7f"},"schema_version":"1.0"},"canonical_sha256":"c88bba5e00ae834721651c859b794d08e783109aa86a536432398ae2fc78d125","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:00.535186Z","signature_b64":"OKsVZtCUM6+/8UYFGNah6HedqfXWBkYD5XCBeS9w+RfNA5CrRzn+YRLjp7YwoLA9TulEs7a12EwviirPfoqwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c88bba5e00ae834721651c859b794d08e783109aa86a536432398ae2fc78d125","last_reissued_at":"2026-07-05T07:03:00.534710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:00.534710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.13284","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":"2026-07-05T07:03:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TgZepQ9ybEF49FYG9OyN42NvxjKmbJwBBbtRVwSca+IgN1J4W0mS7oBy2fRYbpvjc6aGeBakbAvYMni/qnZmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:55:40.368460Z"},"content_sha256":"eec597cb61772fb75cd5964d813996928016a4e538f95569054b1bb3e4947912","schema_version":"1.0","event_id":"sha256:eec597cb61772fb75cd5964d813996928016a4e538f95569054b1bb3e4947912"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZCF3UXQAV2BUOILFDSCZW6KNBD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Recurrent Models with Temporally Local Rules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Azwar Abdulsalam, Joseph G. Makin","submitted_at":"2023-10-20T05:30:30Z","abstract_excerpt":"Fitting generative models to sequential data typically involves two recursive computations through time, one forward and one backward. The latter could be a computation of the loss gradient (as in backpropagation through time), or an inference algorithm (as in the RTS/Kalman smoother). The backward pass in particular is computationally expensive (since it is inherently serial and cannot exploit GPUs), and difficult to map onto biological processes. Work-arounds have been proposed; here we explore a very different one: requiring the generative model to learn the joint distribution over current "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13284","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/2310.13284/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":"2026-07-05T07:03:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7JwEDUU9zbRBetFgWbabiBnigxaWpMDs8CHMhg8PQSTclx8igbdd0SMyCy8qjasf/gwLwqRgHt8h9/iOd+5OBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:55:40.368973Z"},"content_sha256":"26f5bc0c92e654ad3544724135bd8d0e93bffb7e8ab6d025317deefe55e8ec1e","schema_version":"1.0","event_id":"sha256:26f5bc0c92e654ad3544724135bd8d0e93bffb7e8ab6d025317deefe55e8ec1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZCF3UXQAV2BUOILFDSCZW6KNBD/bundle.json","state_url":"https://pith.science/pith/ZCF3UXQAV2BUOILFDSCZW6KNBD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZCF3UXQAV2BUOILFDSCZW6KNBD/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":"2026-08-05T07:55:40Z","links":{"resolver":"https://pith.science/pith/ZCF3UXQAV2BUOILFDSCZW6KNBD","bundle":"https://pith.science/pith/ZCF3UXQAV2BUOILFDSCZW6KNBD/bundle.json","state":"https://pith.science/pith/ZCF3UXQAV2BUOILFDSCZW6KNBD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZCF3UXQAV2BUOILFDSCZW6KNBD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZCF3UXQAV2BUOILFDSCZW6KNBD","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":"0a2706a0bdf3a400eff1c694947131a52990f173ef676841d88eda359cad0d7f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T05:30:30Z","title_canon_sha256":"502dd241cc74f11dfa48bbe6162d2a956432a978c96af25d051f727970cabccb"},"schema_version":"1.0","source":{"id":"2310.13284","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13284","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13284v1","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13284","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZCF3UXQAV2BU","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZCF3UXQAV2BUOILF","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZCF3UXQA","created_at":"2026-07-05T07:03:00Z"}],"graph_snapshots":[{"event_id":"sha256:26f5bc0c92e654ad3544724135bd8d0e93bffb7e8ab6d025317deefe55e8ec1e","target":"graph","created_at":"2026-07-05T07:03:00Z","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/2310.13284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fitting generative models to sequential data typically involves two recursive computations through time, one forward and one backward. The latter could be a computation of the loss gradient (as in backpropagation through time), or an inference algorithm (as in the RTS/Kalman smoother). The backward pass in particular is computationally expensive (since it is inherently serial and cannot exploit GPUs), and difficult to map onto biological processes. Work-arounds have been proposed; here we explore a very different one: requiring the generative model to learn the joint distribution over current ","authors_text":"Azwar Abdulsalam, Joseph G. Makin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T05:30:30Z","title":"Learning Recurrent Models with Temporally Local Rules"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13284","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:eec597cb61772fb75cd5964d813996928016a4e538f95569054b1bb3e4947912","target":"record","created_at":"2026-07-05T07:03:00Z","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":"0a2706a0bdf3a400eff1c694947131a52990f173ef676841d88eda359cad0d7f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T05:30:30Z","title_canon_sha256":"502dd241cc74f11dfa48bbe6162d2a956432a978c96af25d051f727970cabccb"},"schema_version":"1.0","source":{"id":"2310.13284","kind":"arxiv","version":1}},"canonical_sha256":"c88bba5e00ae834721651c859b794d08e783109aa86a536432398ae2fc78d125","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c88bba5e00ae834721651c859b794d08e783109aa86a536432398ae2fc78d125","first_computed_at":"2026-07-05T07:03:00.534710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:00.534710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OKsVZtCUM6+/8UYFGNah6HedqfXWBkYD5XCBeS9w+RfNA5CrRzn+YRLjp7YwoLA9TulEs7a12EwviirPfoqwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:00.535186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13284","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eec597cb61772fb75cd5964d813996928016a4e538f95569054b1bb3e4947912","sha256:26f5bc0c92e654ad3544724135bd8d0e93bffb7e8ab6d025317deefe55e8ec1e"],"state_sha256":"d878f12979b9896c1e1c51b20ddf7c1767d28a4f736f03d3e095cee4dd03ecba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGwH/+00l/FZ/Jcm/kFQSulY4O/RJflxYESakbcqsnxUML9WG9DwF8xDR718ypZJlTfUwSEXb88bud3SXYMsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:55:40.373091Z","bundle_sha256":"1c217e8c7cc3675de92ffbba24bbd3a166dd3736dc17e8b1515599c0ce2f6f20"}}