{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MLZOBHMLBBL3NTGNAZXUYY6U6C","short_pith_number":"pith:MLZOBHML","schema_version":"1.0","canonical_sha256":"62f2e09d8b0857b6cccd066f4c63d4f08de888f8c83014355911b10bf7b682a7","source":{"kind":"arxiv","id":"2502.01342","version":2},"attestation_state":"computed","paper":{"title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Isaac Han, Kyung-Joong Kim, Sangyeon Park, Seungwon Oh","submitted_at":"2025-02-03T13:34:53Z","abstract_excerpt":"Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. This paper introduces AID (Activation by Interval-wise Dropout), a novel method inspired by Dropout, designed to address plasticity loss. Unlike Dropout, AID generates subnetworks by applying Dropout with different probabilities on each preactivation interval. Theoretical analysis reveals that AID regularizes the network, promoting behavior analogous to that of deep linear networks, which do not suffer from plasticity loss. We validate the effectivene"},"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":"2502.01342","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T13:34:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f7f971b3ed5cb6c3c292ccbc878de5a3785b97b4ddaf7adc0d001d08c20ba13a","abstract_canon_sha256":"3ad0fc853e38dd1a7cad78fa4ddaeba5569d35c5ce9b63080f0f1af79f5f79ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:41.736132Z","signature_b64":"OWjYLVRTcz5T64cD2Bi1pLxaZqa8Th2W14AxAL75QJPKD7x9WcAgqnHcwQkXA6rmFoiO0Mh7QZvW65uR73CnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f2e09d8b0857b6cccd066f4c63d4f08de888f8c83014355911b10bf7b682a7","last_reissued_at":"2026-07-05T11:25:41.735680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:41.735680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Isaac Han, Kyung-Joong Kim, Sangyeon Park, Seungwon Oh","submitted_at":"2025-02-03T13:34:53Z","abstract_excerpt":"Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. This paper introduces AID (Activation by Interval-wise Dropout), a novel method inspired by Dropout, designed to address plasticity loss. Unlike Dropout, AID generates subnetworks by applying Dropout with different probabilities on each preactivation interval. Theoretical analysis reveals that AID regularizes the network, promoting behavior analogous to that of deep linear networks, which do not suffer from plasticity loss. We validate the effectivene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01342","kind":"arxiv","version":2},"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/2502.01342/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":"2502.01342","created_at":"2026-07-05T11:25:41.735739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01342v2","created_at":"2026-07-05T11:25:41.735739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01342","created_at":"2026-07-05T11:25:41.735739+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLZOBHMLBBL3","created_at":"2026-07-05T11:25:41.735739+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLZOBHMLBBL3NTGN","created_at":"2026-07-05T11:25:41.735739+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLZOBHML","created_at":"2026-07-05T11:25:41.735739+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/MLZOBHMLBBL3NTGNAZXUYY6U6C","json":"https://pith.science/pith/MLZOBHMLBBL3NTGNAZXUYY6U6C.json","graph_json":"https://pith.science/api/pith-number/MLZOBHMLBBL3NTGNAZXUYY6U6C/graph.json","events_json":"https://pith.science/api/pith-number/MLZOBHMLBBL3NTGNAZXUYY6U6C/events.json","paper":"https://pith.science/paper/MLZOBHML"},"agent_actions":{"view_html":"https://pith.science/pith/MLZOBHMLBBL3NTGNAZXUYY6U6C","download_json":"https://pith.science/pith/MLZOBHMLBBL3NTGNAZXUYY6U6C.json","view_paper":"https://pith.science/paper/MLZOBHML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01342&json=true","fetch_graph":"https://pith.science/api/pith-number/MLZOBHMLBBL3NTGNAZXUYY6U6C/graph.json","fetch_events":"https://pith.science/api/pith-number/MLZOBHMLBBL3NTGNAZXUYY6U6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLZOBHMLBBL3NTGNAZXUYY6U6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLZOBHMLBBL3NTGNAZXUYY6U6C/action/storage_attestation","attest_author":"https://pith.science/pith/MLZOBHMLBBL3NTGNAZXUYY6U6C/action/author_attestation","sign_citation":"https://pith.science/pith/MLZOBHMLBBL3NTGNAZXUYY6U6C/action/citation_signature","submit_replication":"https://pith.science/pith/MLZOBHMLBBL3NTGNAZXUYY6U6C/action/replication_record"}},"created_at":"2026-07-05T11:25:41.735739+00:00","updated_at":"2026-07-05T11:25:41.735739+00:00"}