{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3GMQBVNW327JANSW2U3DT5ZR7V","short_pith_number":"pith:3GMQBVNW","canonical_record":{"source":{"id":"1805.09733","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T15:38:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48e92a0515b99984b6005d70f634722ac4752844885db0e89eb0278735b4856e","abstract_canon_sha256":"b37ecedfe148e5ca462a18df612f88a7c4a6d33ba3122f74ed4ea0036e7e6694"},"schema_version":"1.0"},"canonical_sha256":"d99900d5b6debe903656d53639f731fd7cfa29ab830535353f8a12ebc4f838b0","source":{"kind":"arxiv","id":"1805.09733","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09733","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09733v3","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09733","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"3GMQBVNW327J","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3GMQBVNW327JANSW","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3GMQBVNW","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3GMQBVNW327JANSW2U3DT5ZR7V","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09733","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T15:38:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48e92a0515b99984b6005d70f634722ac4752844885db0e89eb0278735b4856e","abstract_canon_sha256":"b37ecedfe148e5ca462a18df612f88a7c4a6d33ba3122f74ed4ea0036e7e6694"},"schema_version":"1.0"},"canonical_sha256":"d99900d5b6debe903656d53639f731fd7cfa29ab830535353f8a12ebc4f838b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:14.113232Z","signature_b64":"RcT9paWj5u6HaA6khBmLafScjC/ICV4vm6/0pUd6kwy8ww2usVdrIa5tYO/DTAFdbNCv+sKHTkfOx3t/7PZwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d99900d5b6debe903656d53639f731fd7cfa29ab830535353f8a12ebc4f838b0","last_reissued_at":"2026-05-17T23:42:14.112564Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:14.112564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09733","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":"2026-05-17T23:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DSqxcH0IcwUShTRsKVjugmruxVGf+0YfUUjvkH9tKE7EB1ThUhcRHQUSCaBldTqDduQz0kP5IXU9N/uBqkaDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:58:24.089788Z"},"content_sha256":"5066e8153371e5254dab12c9732961608e4358d4c248d825a38a328dc7e0284e","schema_version":"1.0","event_id":"sha256:5066e8153371e5254dab12c9732961608e4358d4c248d825a38a328dc7e0284e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3GMQBVNW327JANSW2U3DT5ZR7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Robust Evaluations of Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Sebastian Farquhar, Yarin Gal","submitted_at":"2018-05-24T15:38:07Z","abstract_excerpt":"Experiments used in current continual learning research do not faithfully assess fundamental challenges of learning continually. Instead of assessing performance on challenging and representative experiment designs, recent research has focused on increased dataset difficulty, while still using flawed experiment set-ups. We examine standard evaluations and show why these evaluations make some continual learning approaches look better than they are. We introduce desiderata for continual learning evaluations and explain why their absence creates misleading comparisons. Based on our desiderata we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09733","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":""},"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":"2026-05-17T23:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/29eWeCV86ZoGxcQ+mx6EEBJ50N35hgmb5YgeDxlHkmDb5qaltqvSycF9+6gR2TKiDbz1r1wayXDL9NWAk0ECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:58:24.090408Z"},"content_sha256":"ce2bb4a17a84c4493a34cde444dc08962c64a27f8eb71efcea55ea5900f20262","schema_version":"1.0","event_id":"sha256:ce2bb4a17a84c4493a34cde444dc08962c64a27f8eb71efcea55ea5900f20262"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GMQBVNW327JANSW2U3DT5ZR7V/bundle.json","state_url":"https://pith.science/pith/3GMQBVNW327JANSW2U3DT5ZR7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GMQBVNW327JANSW2U3DT5ZR7V/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":"2026-05-27T00:58:24Z","links":{"resolver":"https://pith.science/pith/3GMQBVNW327JANSW2U3DT5ZR7V","bundle":"https://pith.science/pith/3GMQBVNW327JANSW2U3DT5ZR7V/bundle.json","state":"https://pith.science/pith/3GMQBVNW327JANSW2U3DT5ZR7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GMQBVNW327JANSW2U3DT5ZR7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3GMQBVNW327JANSW2U3DT5ZR7V","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":"b37ecedfe148e5ca462a18df612f88a7c4a6d33ba3122f74ed4ea0036e7e6694","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T15:38:07Z","title_canon_sha256":"48e92a0515b99984b6005d70f634722ac4752844885db0e89eb0278735b4856e"},"schema_version":"1.0","source":{"id":"1805.09733","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09733","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09733v3","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09733","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"3GMQBVNW327J","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3GMQBVNW327JANSW","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3GMQBVNW","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:ce2bb4a17a84c4493a34cde444dc08962c64a27f8eb71efcea55ea5900f20262","target":"graph","created_at":"2026-05-17T23:42:14Z","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":"Experiments used in current continual learning research do not faithfully assess fundamental challenges of learning continually. Instead of assessing performance on challenging and representative experiment designs, recent research has focused on increased dataset difficulty, while still using flawed experiment set-ups. We examine standard evaluations and show why these evaluations make some continual learning approaches look better than they are. We introduce desiderata for continual learning evaluations and explain why their absence creates misleading comparisons. Based on our desiderata we ","authors_text":"Sebastian Farquhar, Yarin Gal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T15:38:07Z","title":"Towards Robust Evaluations of Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09733","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":"sha256:5066e8153371e5254dab12c9732961608e4358d4c248d825a38a328dc7e0284e","target":"record","created_at":"2026-05-17T23:42:14Z","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":"b37ecedfe148e5ca462a18df612f88a7c4a6d33ba3122f74ed4ea0036e7e6694","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T15:38:07Z","title_canon_sha256":"48e92a0515b99984b6005d70f634722ac4752844885db0e89eb0278735b4856e"},"schema_version":"1.0","source":{"id":"1805.09733","kind":"arxiv","version":3}},"canonical_sha256":"d99900d5b6debe903656d53639f731fd7cfa29ab830535353f8a12ebc4f838b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d99900d5b6debe903656d53639f731fd7cfa29ab830535353f8a12ebc4f838b0","first_computed_at":"2026-05-17T23:42:14.112564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:14.112564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RcT9paWj5u6HaA6khBmLafScjC/ICV4vm6/0pUd6kwy8ww2usVdrIa5tYO/DTAFdbNCv+sKHTkfOx3t/7PZwCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:14.113232Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09733","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5066e8153371e5254dab12c9732961608e4358d4c248d825a38a328dc7e0284e","sha256:ce2bb4a17a84c4493a34cde444dc08962c64a27f8eb71efcea55ea5900f20262"],"state_sha256":"4dadbf9b85cd163e59bb6acc37e386ad1d4376ec16ce740896c49d27f3a26a31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ts2deKZ0rzuI+wkl2gDGIAzemqDZtSaqj2mJKrZ9gclCbQ8IxwDLPapum2N6zzdIGdON1dbShjLyDBXi/i5CCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T00:58:24.094263Z","bundle_sha256":"d8191b644c1941b51a3076e1d2c4eba348c3720c7e63591c7501bba83e3ec44c"}}