{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NPZCZGHRUW3TJ3XBCG7SXVRWIC","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":"ee66316929fed7c45ab363e3dd072d5b3bccf4f4c90e616cdab3150e0ea849a6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T06:29:54Z","title_canon_sha256":"ab52c1d23c72d8bdc9f28b6ab0fc8f8443da1fdd5d2dc594dfb602fb083acfab"},"schema_version":"1.0","source":{"id":"2403.07356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07356","created_at":"2026-07-05T07:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07356v1","created_at":"2026-07-05T07:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07356","created_at":"2026-07-05T07:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"NPZCZGHRUW3T","created_at":"2026-07-05T07:55:02Z"},{"alias_kind":"pith_short_16","alias_value":"NPZCZGHRUW3TJ3XB","created_at":"2026-07-05T07:55:02Z"},{"alias_kind":"pith_short_8","alias_value":"NPZCZGHR","created_at":"2026-07-05T07:55:02Z"}],"graph_snapshots":[{"event_id":"sha256:cbd307fd54a87864be44a2d3aa044c709c5df6afa1fcf1d32c66ab435618725c","target":"graph","created_at":"2026-07-05T07:55:02Z","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/2403.07356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task changes are completely unpredictable. Given a description of an overarching goal or data theme, which we call a realm, humans can often guess what concepts are associated with it. We show here that the combination of a large language model and an image generation model can similarly provide useful premonitions as to how a continual learning challenge might develop over time. We use the large language model to genera","authors_text":"Anton van den Hengel, Dong Gong, Ehsan Abbasnejad, Mark D. McDonnell","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T06:29:54Z","title":"Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07356","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":"sha256:9fd3b17fd40a85e2879dd722d09d120acec84912416a20365a36d09b40ae5e3b","target":"record","created_at":"2026-07-05T07:55:02Z","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":"ee66316929fed7c45ab363e3dd072d5b3bccf4f4c90e616cdab3150e0ea849a6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T06:29:54Z","title_canon_sha256":"ab52c1d23c72d8bdc9f28b6ab0fc8f8443da1fdd5d2dc594dfb602fb083acfab"},"schema_version":"1.0","source":{"id":"2403.07356","kind":"arxiv","version":1}},"canonical_sha256":"6bf22c98f1a5b734eee111bf2bd63640a695f23dd3fbd8373e71132103801ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bf22c98f1a5b734eee111bf2bd63640a695f23dd3fbd8373e71132103801ffb","first_computed_at":"2026-07-05T07:55:02.519587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:02.519587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ho/IIt59Az88oWLsniSV3zkHE1p010Fb/8qpt+ArNpQ4W9DAFvb7k2YWnj6Ut26vzd77D9OlBb1hrHhcrFb1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:02.519952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fd3b17fd40a85e2879dd722d09d120acec84912416a20365a36d09b40ae5e3b","sha256:cbd307fd54a87864be44a2d3aa044c709c5df6afa1fcf1d32c66ab435618725c"],"state_sha256":"f02b58e00267df3b64b7d25f7d563998ef5343d5a009f6daac3e827080e2be63"}