{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7K4GITEHBRHGQYYA4OFXN4UGRF","short_pith_number":"pith:7K4GITEH","schema_version":"1.0","canonical_sha256":"fab8644c870c4e686300e38b76f28689563e6a6588b2a92ee21f276a7b1ea20c","source":{"kind":"arxiv","id":"1808.06396","version":1},"attestation_state":"computed","paper":{"title":"DeeSIL: Deep-Shallow Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrian Popescu, Eden Belouadah","submitted_at":"2018-08-20T11:39:09Z","abstract_excerpt":"Incremental Learning (IL) is an interesting AI problem when the algorithm is assumed to work on a budget. This is especially true when IL is modeled using a deep learning approach, where two com- plex challenges arise due to limited memory, which induces catastrophic forgetting and delays related to the retraining needed in order to incorpo- rate new classes. Here we introduce DeeSIL, an adaptation of a known transfer learning scheme that combines a fixed deep representation used as feature extractor and learning independent shallow classifiers to in- crease recognition capacity. This scheme t"},"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":"1808.06396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-20T11:39:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"07a332a270d445645f8c21750ecc7b1a67c604e7223f515ae71cd1f704982e84","abstract_canon_sha256":"86367a6bfcfa76709c42a2c3eb579cdfb042802de2294574d68ecfdef6d37c32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:45.100556Z","signature_b64":"rPsOtSLpW6sYeOvuyRQzDgsH9Y9fUqV0YLjJtvezb3wSXMEN7SdqrDhVq+z+7lL3SKOyIfkUOQRP3G6inAnDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fab8644c870c4e686300e38b76f28689563e6a6588b2a92ee21f276a7b1ea20c","last_reissued_at":"2026-05-18T00:07:45.099903Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:45.099903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeeSIL: Deep-Shallow Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrian Popescu, Eden Belouadah","submitted_at":"2018-08-20T11:39:09Z","abstract_excerpt":"Incremental Learning (IL) is an interesting AI problem when the algorithm is assumed to work on a budget. This is especially true when IL is modeled using a deep learning approach, where two com- plex challenges arise due to limited memory, which induces catastrophic forgetting and delays related to the retraining needed in order to incorpo- rate new classes. Here we introduce DeeSIL, an adaptation of a known transfer learning scheme that combines a fixed deep representation used as feature extractor and learning independent shallow classifiers to in- crease recognition capacity. This scheme t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06396","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":"1808.06396","created_at":"2026-05-18T00:07:45.100000+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.06396v1","created_at":"2026-05-18T00:07:45.100000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06396","created_at":"2026-05-18T00:07:45.100000+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K4GITEHBRHG","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K4GITEHBRHGQYYA","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K4GITEH","created_at":"2026-05-18T12:32:11.075285+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/7K4GITEHBRHGQYYA4OFXN4UGRF","json":"https://pith.science/pith/7K4GITEHBRHGQYYA4OFXN4UGRF.json","graph_json":"https://pith.science/api/pith-number/7K4GITEHBRHGQYYA4OFXN4UGRF/graph.json","events_json":"https://pith.science/api/pith-number/7K4GITEHBRHGQYYA4OFXN4UGRF/events.json","paper":"https://pith.science/paper/7K4GITEH"},"agent_actions":{"view_html":"https://pith.science/pith/7K4GITEHBRHGQYYA4OFXN4UGRF","download_json":"https://pith.science/pith/7K4GITEHBRHGQYYA4OFXN4UGRF.json","view_paper":"https://pith.science/paper/7K4GITEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.06396&json=true","fetch_graph":"https://pith.science/api/pith-number/7K4GITEHBRHGQYYA4OFXN4UGRF/graph.json","fetch_events":"https://pith.science/api/pith-number/7K4GITEHBRHGQYYA4OFXN4UGRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K4GITEHBRHGQYYA4OFXN4UGRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K4GITEHBRHGQYYA4OFXN4UGRF/action/storage_attestation","attest_author":"https://pith.science/pith/7K4GITEHBRHGQYYA4OFXN4UGRF/action/author_attestation","sign_citation":"https://pith.science/pith/7K4GITEHBRHGQYYA4OFXN4UGRF/action/citation_signature","submit_replication":"https://pith.science/pith/7K4GITEHBRHGQYYA4OFXN4UGRF/action/replication_record"}},"created_at":"2026-05-18T00:07:45.100000+00:00","updated_at":"2026-05-18T00:07:45.100000+00:00"}