{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2KNHSISIEW3U7MIPL3NDVFM3RK","short_pith_number":"pith:2KNHSISI","schema_version":"1.0","canonical_sha256":"d29a79224825b74fb10f5eda3a959b8aa49b31ee6ba75b36d6a50ae91fbfbb08","source":{"kind":"arxiv","id":"1907.09695","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Compression-based Lifelong Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Devis Tuia, Matthew B. Blaschko, Maxim Berman, Shivangi Srivastava","submitted_at":"2019-07-23T04:58:52Z","abstract_excerpt":"The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two major ways to mitigate this problem: either preserving activations of the initial network during training with a new task; or restricting the new network activations to remain close to the initial ones. The latter approach falls under the denomination of lifelong learning, where the model is updated in a way that it performs well on both old and new tasks, without having access to the old task's training samples anymor"},"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":"1907.09695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-23T04:58:52Z","cross_cats_sorted":[],"title_canon_sha256":"1378c3011ab4656c4427a0a48e59212e00ff4f28c168d4dedea54ba80d18c23e","abstract_canon_sha256":"d778742fe47f2d507b8f3d4effe7ac12601107cd4b6d17afcc867241a24ac5a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:50.386272Z","signature_b64":"zp+df91XVCVbtcdmP9i8apFwj4Q2MCGs2H7bkyznBCqgEbc3FACmy3MYv1j+4xRDxDaczEFGishRg3kTow9ZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d29a79224825b74fb10f5eda3a959b8aa49b31ee6ba75b36d6a50ae91fbfbb08","last_reissued_at":"2026-05-17T23:39:50.385738Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:50.385738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Compression-based Lifelong Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Devis Tuia, Matthew B. Blaschko, Maxim Berman, Shivangi Srivastava","submitted_at":"2019-07-23T04:58:52Z","abstract_excerpt":"The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two major ways to mitigate this problem: either preserving activations of the initial network during training with a new task; or restricting the new network activations to remain close to the initial ones. The latter approach falls under the denomination of lifelong learning, where the model is updated in a way that it performs well on both old and new tasks, without having access to the old task's training samples anymor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09695","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":""},"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":"1907.09695","created_at":"2026-05-17T23:39:50.385816+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.09695v1","created_at":"2026-05-17T23:39:50.385816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09695","created_at":"2026-05-17T23:39:50.385816+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KNHSISIEW3U","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KNHSISIEW3U7MIP","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KNHSISI","created_at":"2026-05-18T12:33:07.085635+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/2KNHSISIEW3U7MIPL3NDVFM3RK","json":"https://pith.science/pith/2KNHSISIEW3U7MIPL3NDVFM3RK.json","graph_json":"https://pith.science/api/pith-number/2KNHSISIEW3U7MIPL3NDVFM3RK/graph.json","events_json":"https://pith.science/api/pith-number/2KNHSISIEW3U7MIPL3NDVFM3RK/events.json","paper":"https://pith.science/paper/2KNHSISI"},"agent_actions":{"view_html":"https://pith.science/pith/2KNHSISIEW3U7MIPL3NDVFM3RK","download_json":"https://pith.science/pith/2KNHSISIEW3U7MIPL3NDVFM3RK.json","view_paper":"https://pith.science/paper/2KNHSISI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.09695&json=true","fetch_graph":"https://pith.science/api/pith-number/2KNHSISIEW3U7MIPL3NDVFM3RK/graph.json","fetch_events":"https://pith.science/api/pith-number/2KNHSISIEW3U7MIPL3NDVFM3RK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KNHSISIEW3U7MIPL3NDVFM3RK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KNHSISIEW3U7MIPL3NDVFM3RK/action/storage_attestation","attest_author":"https://pith.science/pith/2KNHSISIEW3U7MIPL3NDVFM3RK/action/author_attestation","sign_citation":"https://pith.science/pith/2KNHSISIEW3U7MIPL3NDVFM3RK/action/citation_signature","submit_replication":"https://pith.science/pith/2KNHSISIEW3U7MIPL3NDVFM3RK/action/replication_record"}},"created_at":"2026-05-17T23:39:50.385816+00:00","updated_at":"2026-05-17T23:39:50.385816+00:00"}