{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Q44ECVFV4MDHNBMXZMECH26KDS","short_pith_number":"pith:Q44ECVFV","schema_version":"1.0","canonical_sha256":"87384154b5e306768597cb0823ebca1caed628a0c17a5868484c5bcf599a234f","source":{"kind":"arxiv","id":"1902.10486","version":4},"attestation_state":"computed","paper":{"title":"On Tiny Episodic Memories in Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, Mohamed Elhoseiny, Philip H. S. Torr, Puneet K. Dokania, Thalaiyasingam Ajanthan","submitted_at":"2019-02-27T12:34:19Z","abstract_excerpt":"In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform previous tasks. One way to endow the learner the ability to perform tasks seen in the past is to store a small memory, dubbed episodic memory, that stores few examples from previous tasks and then to replay these examples when training for future tasks. In this work, we empirical"},"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":"1902.10486","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T12:34:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1bf3a7f46433e41767701fd80d298e16edf90552d2d22e5935f7a7a392a87643","abstract_canon_sha256":"5fade90bff33a3e6185e3ee9a534e0fdf89799920583443f5e8e8a8594600ac7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:21.565563Z","signature_b64":"+Gx31jppNMTyR2DzW1Rkch5kfCgVAHwR16oqMB4tuRzK9NU+W3Pb5tzjIMkKcb3yRwpHGSg85moZee0aob30DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87384154b5e306768597cb0823ebca1caed628a0c17a5868484c5bcf599a234f","last_reissued_at":"2026-05-17T23:44:21.564943Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:21.564943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Tiny Episodic Memories in Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, Mohamed Elhoseiny, Philip H. S. Torr, Puneet K. Dokania, Thalaiyasingam Ajanthan","submitted_at":"2019-02-27T12:34:19Z","abstract_excerpt":"In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform previous tasks. One way to endow the learner the ability to perform tasks seen in the past is to store a small memory, dubbed episodic memory, that stores few examples from previous tasks and then to replay these examples when training for future tasks. In this work, we empirical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10486","kind":"arxiv","version":4},"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":"1902.10486","created_at":"2026-05-17T23:44:21.565034+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10486v4","created_at":"2026-05-17T23:44:21.565034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10486","created_at":"2026-05-17T23:44:21.565034+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q44ECVFV4MDH","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q44ECVFV4MDHNBMX","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q44ECVFV","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":35,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2411.04680","citing_title":"Privacy Leakage via Output Label Space and Differentially Private Continual Learning","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2412.13050","citing_title":"Modality-Inconsistent Continual Learning of Multimodal Large Language Models","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22454","citing_title":"Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2601.09512","citing_title":"CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2602.10503","citing_title":"Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20296","citing_title":"Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20297","citing_title":"MedCRP-CL: Continual Medical Image Segmentation via Bayesian Nonparametric Semantic Modality Discovery","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16353","citing_title":"StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11617","citing_title":"MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15775","citing_title":"Continual Learning of Domain-Invariant Representations","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17729","citing_title":"Domain Incremental Learning for Pandemic-Resilient Chest X-Ray Analysis","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19080","citing_title":"MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19145","citing_title":"PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19201","citing_title":"On-Device Continual Learning with Dual-Stage Buffer and Dynamic Loss for Point-of-Care Pneumonia Diagnosis","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15053","citing_title":"TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15384","citing_title":"Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2505.20049","citing_title":"Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2508.18187","citing_title":"BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2312.03732","citing_title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22479","citing_title":"Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2603.14632","citing_title":"Continual Few-shot Adaptation for Synthetic Fingerprint Detection","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2603.20410","citing_title":"SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12998","citing_title":"DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12998","citing_title":"DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13162","citing_title":"Continual Fine-Tuning of Large Language Models via Program Memory","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS","json":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS.json","graph_json":"https://pith.science/api/pith-number/Q44ECVFV4MDHNBMXZMECH26KDS/graph.json","events_json":"https://pith.science/api/pith-number/Q44ECVFV4MDHNBMXZMECH26KDS/events.json","paper":"https://pith.science/paper/Q44ECVFV"},"agent_actions":{"view_html":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS","download_json":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS.json","view_paper":"https://pith.science/paper/Q44ECVFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10486&json=true","fetch_graph":"https://pith.science/api/pith-number/Q44ECVFV4MDHNBMXZMECH26KDS/graph.json","fetch_events":"https://pith.science/api/pith-number/Q44ECVFV4MDHNBMXZMECH26KDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS/action/storage_attestation","attest_author":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS/action/author_attestation","sign_citation":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS/action/citation_signature","submit_replication":"https://pith.science/pith/Q44ECVFV4MDHNBMXZMECH26KDS/action/replication_record"}},"created_at":"2026-05-17T23:44:21.565034+00:00","updated_at":"2026-05-17T23:44:21.565034+00:00"}