{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WYGOJ7RAFSHZXKKHILRMABLDWF","short_pith_number":"pith:WYGOJ7RA","schema_version":"1.0","canonical_sha256":"b60ce4fe202c8f9ba94742e2c00563b142b6f1d367cec5f7a453b1b3bcf8af8a","source":{"kind":"arxiv","id":"2511.04666","version":4},"attestation_state":"computed","paper":{"title":"Forgetting is Everywhere","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aidan Scannell, Amos Storkey, Ben Sanati, David Abel, Esmeralda S. Whitammer, Thomas L. Lee, Trevor McInroe","submitted_at":"2025-11-06T18:52:57Z","abstract_excerpt":"A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge as they adapt to new data. Addressing this problem requires a principled understanding of forgetting. Yet, despite decades of study, no unified definition has emerged that offers insight into the underlying dynamics of learning. We propose an algorithm- and task-agnostic theory that characterises forgetting as a lack of self-consistency in a learner's predictive distribution, manifesting as a loss of predictive information. Our theory naturally yields a general measure of an algorithm's"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2511.04666","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-06T18:52:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2bdde45e1d081e5c0cf5ece0de2eff35c772fa5ca95488ab584037a15cd4f3c4","abstract_canon_sha256":"38ea9b6f4721f6f28e7577d5b354475567336d6442b9071ed463df18bc74ca33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:20.549564Z","signature_b64":"NfAYDB2JuUGpXIrzbwoOa5Rj6QgcSpJ6QcfaoW1sssOFxfHFxd+WLWQQcui4RsPkXIJ4a0PnccceDs87JbgWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b60ce4fe202c8f9ba94742e2c00563b142b6f1d367cec5f7a453b1b3bcf8af8a","last_reissued_at":"2026-07-28T02:23:20.548602Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:20.548602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forgetting is Everywhere","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aidan Scannell, Amos Storkey, Ben Sanati, David Abel, Esmeralda S. Whitammer, Thomas L. Lee, Trevor McInroe","submitted_at":"2025-11-06T18:52:57Z","abstract_excerpt":"A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge as they adapt to new data. Addressing this problem requires a principled understanding of forgetting. Yet, despite decades of study, no unified definition has emerged that offers insight into the underlying dynamics of learning. We propose an algorithm- and task-agnostic theory that characterises forgetting as a lack of self-consistency in a learner's predictive distribution, manifesting as a loss of predictive information. Our theory naturally yields a general measure of an algorithm's"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.04666","kind":"arxiv","version":4},"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/2511.04666/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2511.04666","created_at":"2026-07-28T02:23:20.549048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.04666v4","created_at":"2026-07-28T02:23:20.549048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.04666","created_at":"2026-07-28T02:23:20.549048+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYGOJ7RAFSHZ","created_at":"2026-07-28T02:23:20.549048+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYGOJ7RAFSHZXKKH","created_at":"2026-07-28T02:23:20.549048+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYGOJ7RA","created_at":"2026-07-28T02:23:20.549048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF","json":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF.json","graph_json":"https://pith.science/api/pith-number/WYGOJ7RAFSHZXKKHILRMABLDWF/graph.json","events_json":"https://pith.science/api/pith-number/WYGOJ7RAFSHZXKKHILRMABLDWF/events.json","paper":"https://pith.science/paper/WYGOJ7RA"},"agent_actions":{"view_html":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF","download_json":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF.json","view_paper":"https://pith.science/paper/WYGOJ7RA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.04666&json=true","fetch_graph":"https://pith.science/api/pith-number/WYGOJ7RAFSHZXKKHILRMABLDWF/graph.json","fetch_events":"https://pith.science/api/pith-number/WYGOJ7RAFSHZXKKHILRMABLDWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF/action/storage_attestation","attest_author":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF/action/author_attestation","sign_citation":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF/action/citation_signature","submit_replication":"https://pith.science/pith/WYGOJ7RAFSHZXKKHILRMABLDWF/action/replication_record"}},"created_at":"2026-07-28T02:23:20.549048+00:00","updated_at":"2026-07-28T02:23:20.549048+00:00"}