{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7ZNW3S5ZV5RQ2SX6MWEJVFRS46","short_pith_number":"pith:7ZNW3S5Z","canonical_record":{"source":{"id":"2201.06534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T17:29:16Z","cross_cats_sorted":[],"title_canon_sha256":"8e19cbc725f4ddfb755127ff2aa948b1a184963ca9ccd57312fefdf028532fef","abstract_canon_sha256":"69a3002ecc127310360a55c856d1af022435efb34209dca93941d005064283b1"},"schema_version":"1.0"},"canonical_sha256":"fe5b6dcbb9af630d4afe65889a9632e7b9ab3405415204d1356b26785e069f2c","source":{"kind":"arxiv","id":"2201.06534","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06534","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06534v1","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06534","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"7ZNW3S5ZV5RQ","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"pith_short_16","alias_value":"7ZNW3S5ZV5RQ2SX6","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"pith_short_8","alias_value":"7ZNW3S5Z","created_at":"2026-07-05T03:48:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7ZNW3S5ZV5RQ2SX6MWEJVFRS46","target":"record","payload":{"canonical_record":{"source":{"id":"2201.06534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T17:29:16Z","cross_cats_sorted":[],"title_canon_sha256":"8e19cbc725f4ddfb755127ff2aa948b1a184963ca9ccd57312fefdf028532fef","abstract_canon_sha256":"69a3002ecc127310360a55c856d1af022435efb34209dca93941d005064283b1"},"schema_version":"1.0"},"canonical_sha256":"fe5b6dcbb9af630d4afe65889a9632e7b9ab3405415204d1356b26785e069f2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:59.296545Z","signature_b64":"/9AqOu7DzvKs/BgtVhqvcHeYFIFnKuMOSz0WARKYtji21dDRbAE2yKSPHgugndybLvYZLtEGK0OilLL3RfdrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe5b6dcbb9af630d4afe65889a9632e7b9ab3405415204d1356b26785e069f2c","last_reissued_at":"2026-07-05T03:48:59.296204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:59.296204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.06534","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":"2026-07-05T03:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20Uy/YegiXBMnaBZITUZxUDvnAdBgWvAZ7N0E6Fs1+gmHfmJbF2yzWd6P2QNDKqulnw+uhFOgcEWvD+rH0vRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:40:51.052277Z"},"content_sha256":"ac80478f3df40c9cae08b6de417fe6647d4e0511f07f52535e776eb3f79fb260","schema_version":"1.0","event_id":"sha256:ac80478f3df40c9cae08b6de417fe6647d4e0511f07f52535e776eb3f79fb260"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7ZNW3S5ZV5RQ2SX6MWEJVFRS46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Logarithmic Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Marczak, Kamil Deja, Pawe{\\l} Wawrzy\\'nski, Tomasz Trzci\\'nski, Wojciech Masarczyk","submitted_at":"2022-01-17T17:29:16Z","abstract_excerpt":"We introduce a neural network architecture that logarithmically reduces the number of self-rehearsal steps in the generative rehearsal of continually learned models. In continual learning (CL), training samples come in subsequent tasks, and the trained model can access only a single task at a time. To replay previous samples, contemporary CL methods bootstrap generative models and train them recursively with a combination of current and regenerated past data. This recurrence leads to superfluous computations as the same past samples are regenerated after each task, and the reconstruction quali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06534","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/2201.06534/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":"2026-07-05T03:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kGPaDTpNSyBM0UPoH5kgLgF7/en/eE3Dl9m+JwQUlqH1vahwCbIXd/kncSl1rNQ+Xk18KYS07JcpVmR8dC0cDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:40:51.053159Z"},"content_sha256":"808a44cb748061b3af40b2d5a4021aadf71a5a09965a53cd98a45f06eb6f43d2","schema_version":"1.0","event_id":"sha256:808a44cb748061b3af40b2d5a4021aadf71a5a09965a53cd98a45f06eb6f43d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ZNW3S5ZV5RQ2SX6MWEJVFRS46/bundle.json","state_url":"https://pith.science/pith/7ZNW3S5ZV5RQ2SX6MWEJVFRS46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ZNW3S5ZV5RQ2SX6MWEJVFRS46/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":"2026-08-18T10:40:51Z","links":{"resolver":"https://pith.science/pith/7ZNW3S5ZV5RQ2SX6MWEJVFRS46","bundle":"https://pith.science/pith/7ZNW3S5ZV5RQ2SX6MWEJVFRS46/bundle.json","state":"https://pith.science/pith/7ZNW3S5ZV5RQ2SX6MWEJVFRS46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ZNW3S5ZV5RQ2SX6MWEJVFRS46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7ZNW3S5ZV5RQ2SX6MWEJVFRS46","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":"69a3002ecc127310360a55c856d1af022435efb34209dca93941d005064283b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T17:29:16Z","title_canon_sha256":"8e19cbc725f4ddfb755127ff2aa948b1a184963ca9ccd57312fefdf028532fef"},"schema_version":"1.0","source":{"id":"2201.06534","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06534","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06534v1","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06534","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"7ZNW3S5ZV5RQ","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"pith_short_16","alias_value":"7ZNW3S5ZV5RQ2SX6","created_at":"2026-07-05T03:48:59Z"},{"alias_kind":"pith_short_8","alias_value":"7ZNW3S5Z","created_at":"2026-07-05T03:48:59Z"}],"graph_snapshots":[{"event_id":"sha256:808a44cb748061b3af40b2d5a4021aadf71a5a09965a53cd98a45f06eb6f43d2","target":"graph","created_at":"2026-07-05T03:48:59Z","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/2201.06534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a neural network architecture that logarithmically reduces the number of self-rehearsal steps in the generative rehearsal of continually learned models. In continual learning (CL), training samples come in subsequent tasks, and the trained model can access only a single task at a time. To replay previous samples, contemporary CL methods bootstrap generative models and train them recursively with a combination of current and regenerated past data. This recurrence leads to superfluous computations as the same past samples are regenerated after each task, and the reconstruction quali","authors_text":"Daniel Marczak, Kamil Deja, Pawe{\\l} Wawrzy\\'nski, Tomasz Trzci\\'nski, Wojciech Masarczyk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T17:29:16Z","title":"Logarithmic Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06534","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:ac80478f3df40c9cae08b6de417fe6647d4e0511f07f52535e776eb3f79fb260","target":"record","created_at":"2026-07-05T03:48:59Z","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":"69a3002ecc127310360a55c856d1af022435efb34209dca93941d005064283b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T17:29:16Z","title_canon_sha256":"8e19cbc725f4ddfb755127ff2aa948b1a184963ca9ccd57312fefdf028532fef"},"schema_version":"1.0","source":{"id":"2201.06534","kind":"arxiv","version":1}},"canonical_sha256":"fe5b6dcbb9af630d4afe65889a9632e7b9ab3405415204d1356b26785e069f2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe5b6dcbb9af630d4afe65889a9632e7b9ab3405415204d1356b26785e069f2c","first_computed_at":"2026-07-05T03:48:59.296204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:59.296204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/9AqOu7DzvKs/BgtVhqvcHeYFIFnKuMOSz0WARKYtji21dDRbAE2yKSPHgugndybLvYZLtEGK0OilLL3RfdrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:59.296545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.06534","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac80478f3df40c9cae08b6de417fe6647d4e0511f07f52535e776eb3f79fb260","sha256:808a44cb748061b3af40b2d5a4021aadf71a5a09965a53cd98a45f06eb6f43d2"],"state_sha256":"7718e7285cef3f7850f0ac5697fa1972cf968c3368445adb5688a17c5e39d0d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zv7VwYXK881XMsDFfyyUzKyxT+VJpym1W9KaMq65p5CXk44t3o4iU4Yk+jfpotOxvExrLYOs8rqUsye8zTNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T10:40:51.058311Z","bundle_sha256":"854928e12ee8b11c029021a569341e4eaaa2d1d06550aa631ae6208652850981"}}