{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ULIAI2AACMOIHE54AFS2V77AYY","short_pith_number":"pith:ULIAI2AA","schema_version":"1.0","canonical_sha256":"a2d0046800131c8393bc0165aaffe0c628ca36bc0b004a998c4dbe10791e1a44","source":{"kind":"arxiv","id":"2202.05411","version":3},"attestation_state":"computed","paper":{"title":"Incremental Learning of Structured Memory via Closed-Loop Transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brent Yi, Mingyang Li, Shengbang Tong, Xili Dai, Yi Ma, Ziyang Wu","submitted_at":"2022-02-11T02:20:43Z","abstract_excerpt":"This work proposes a minimal computational model for learning structured memories of multiple object classes in an incremental setting. Our approach is based on establishing a closed-loop transcription between the classes and a corresponding set of subspaces, known as a linear discriminative representation, in a low-dimensional feature space. Our method is simpler than existing approaches for incremental learning, and more efficient in terms of model size, storage, and computation: it requires only a single, fixed-capacity autoencoding network with a feature space that is used for both discrim"},"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":"2202.05411","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-11T02:20:43Z","cross_cats_sorted":[],"title_canon_sha256":"af3caa054dcdd7c7855632a4b0b9f080e4e815542cb86cd7e2e61fee750d3f63","abstract_canon_sha256":"3a4aabb59bded6369d538294c9d2717da2db1dfb11ff6ba77a40d84c257fbf12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:15.648541Z","signature_b64":"BPy32ruw5nDvzrHzVFsAAvZk5r1pKIK0HnBZhk8kYThSq4DxpgCkvfnZXvwx3U5A8APCsNJyiWGg3IrG5AP6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d0046800131c8393bc0165aaffe0c628ca36bc0b004a998c4dbe10791e1a44","last_reissued_at":"2026-07-05T06:18:15.648053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:15.648053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental Learning of Structured Memory via Closed-Loop Transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brent Yi, Mingyang Li, Shengbang Tong, Xili Dai, Yi Ma, Ziyang Wu","submitted_at":"2022-02-11T02:20:43Z","abstract_excerpt":"This work proposes a minimal computational model for learning structured memories of multiple object classes in an incremental setting. Our approach is based on establishing a closed-loop transcription between the classes and a corresponding set of subspaces, known as a linear discriminative representation, in a low-dimensional feature space. Our method is simpler than existing approaches for incremental learning, and more efficient in terms of model size, storage, and computation: it requires only a single, fixed-capacity autoencoding network with a feature space that is used for both discrim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05411","kind":"arxiv","version":3},"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/2202.05411/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":"2202.05411","created_at":"2026-07-05T06:18:15.648109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.05411v3","created_at":"2026-07-05T06:18:15.648109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05411","created_at":"2026-07-05T06:18:15.648109+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULIAI2AACMOI","created_at":"2026-07-05T06:18:15.648109+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULIAI2AACMOIHE54","created_at":"2026-07-05T06:18:15.648109+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULIAI2AA","created_at":"2026-07-05T06:18:15.648109+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22408","citing_title":"Frugal Incremental Generative Modeling using Variational Autoencoders","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY","json":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY.json","graph_json":"https://pith.science/api/pith-number/ULIAI2AACMOIHE54AFS2V77AYY/graph.json","events_json":"https://pith.science/api/pith-number/ULIAI2AACMOIHE54AFS2V77AYY/events.json","paper":"https://pith.science/paper/ULIAI2AA"},"agent_actions":{"view_html":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY","download_json":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY.json","view_paper":"https://pith.science/paper/ULIAI2AA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.05411&json=true","fetch_graph":"https://pith.science/api/pith-number/ULIAI2AACMOIHE54AFS2V77AYY/graph.json","fetch_events":"https://pith.science/api/pith-number/ULIAI2AACMOIHE54AFS2V77AYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY/action/storage_attestation","attest_author":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY/action/author_attestation","sign_citation":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY/action/citation_signature","submit_replication":"https://pith.science/pith/ULIAI2AACMOIHE54AFS2V77AYY/action/replication_record"}},"created_at":"2026-07-05T06:18:15.648109+00:00","updated_at":"2026-07-05T06:18:15.648109+00:00"}