{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:22OEA4D3ANKXOU4GFADBKOOKJN","short_pith_number":"pith:22OEA4D3","schema_version":"1.0","canonical_sha256":"d69c40707b035577538628061539ca4b7a0bc9eb84151258b427551c71d4372e","source":{"kind":"arxiv","id":"2006.06958","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Role of Training Regimes in Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hassan Ghasemzadeh, Mehrdad Farajtabar, Razvan Pascanu, Seyed Iman Mirzadeh","submitted_at":"2020-06-12T06:00:27Z","abstract_excerpt":"Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. From the perspective of the well established plasticity-stability dilemma, neural networks tend to be overly plastic, lacking the stability necessary to prevent the forgetting of previous knowledge, which means that as learning progresses, networks tend to forget previously seen tasks. This phenomenon coined in the continual learning literature, has attracted much attention lately, and several families of approaches have been proposed with different degrees of success. "},"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":"2006.06958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T06:00:27Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"8cb623d9f78adec1327e03e73f28ed3cc022be511e3a7b1b2f7893292475efd2","abstract_canon_sha256":"9edcb8c8d770bda3af66031b61cd85b8ce765be05e853da48784a0a6534508dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:48.528746Z","signature_b64":"PQLj7z3e26acrNAjpIZ8bZkuwAntlOpqv7HLSWmYoxP0j0cO+hlHxmBaILZPjf2FGSyxR4uXybE2h5MGKtyvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d69c40707b035577538628061539ca4b7a0bc9eb84151258b427551c71d4372e","last_reissued_at":"2026-07-05T01:09:48.528280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:48.528280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Role of Training Regimes in Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hassan Ghasemzadeh, Mehrdad Farajtabar, Razvan Pascanu, Seyed Iman Mirzadeh","submitted_at":"2020-06-12T06:00:27Z","abstract_excerpt":"Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. From the perspective of the well established plasticity-stability dilemma, neural networks tend to be overly plastic, lacking the stability necessary to prevent the forgetting of previous knowledge, which means that as learning progresses, networks tend to forget previously seen tasks. This phenomenon coined in the continual learning literature, has attracted much attention lately, and several families of approaches have been proposed with different degrees of success. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06958","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/2006.06958/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":"2006.06958","created_at":"2026-07-05T01:09:48.528333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06958v1","created_at":"2026-07-05T01:09:48.528333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06958","created_at":"2026-07-05T01:09:48.528333+00:00"},{"alias_kind":"pith_short_12","alias_value":"22OEA4D3ANKX","created_at":"2026-07-05T01:09:48.528333+00:00"},{"alias_kind":"pith_short_16","alias_value":"22OEA4D3ANKXOU4G","created_at":"2026-07-05T01:09:48.528333+00:00"},{"alias_kind":"pith_short_8","alias_value":"22OEA4D3","created_at":"2026-07-05T01:09:48.528333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16426","citing_title":"Functional Similarity Metric for Neural Networks: Overcoming Parametric Ambiguity via Activation Region Analysis","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN","json":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN.json","graph_json":"https://pith.science/api/pith-number/22OEA4D3ANKXOU4GFADBKOOKJN/graph.json","events_json":"https://pith.science/api/pith-number/22OEA4D3ANKXOU4GFADBKOOKJN/events.json","paper":"https://pith.science/paper/22OEA4D3"},"agent_actions":{"view_html":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN","download_json":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN.json","view_paper":"https://pith.science/paper/22OEA4D3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06958&json=true","fetch_graph":"https://pith.science/api/pith-number/22OEA4D3ANKXOU4GFADBKOOKJN/graph.json","fetch_events":"https://pith.science/api/pith-number/22OEA4D3ANKXOU4GFADBKOOKJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN/action/storage_attestation","attest_author":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN/action/author_attestation","sign_citation":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN/action/citation_signature","submit_replication":"https://pith.science/pith/22OEA4D3ANKXOU4GFADBKOOKJN/action/replication_record"}},"created_at":"2026-07-05T01:09:48.528333+00:00","updated_at":"2026-07-05T01:09:48.528333+00:00"}