{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HSCSJ2LBX4QE4WEPVX76XOS7EA","short_pith_number":"pith:HSCSJ2LB","schema_version":"1.0","canonical_sha256":"3c8524e961bf204e588fadffebba5f2024c7946c02ff9a99dbf870249e80f76d","source":{"kind":"arxiv","id":"2401.02576","version":2},"attestation_state":"computed","paper":{"title":"t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Peter Stone, William Yue","submitted_at":"2024-01-04T23:44:35Z","abstract_excerpt":"Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously encountered tasks to augment the current dataset. However, existing deep generative replay methods for continual learning rely on autoregressive models, which suffer from compounding errors in the generated trajectories. In this paper, we propose a simple, scalable, and non-autoregressive method for continual learning in decision-making tasks using a generative mode"},"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":"2401.02576","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-04T23:44:35Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"d24ff21711f8d8b20c921a7585d6acbbf6d58be95cdfef1d72ce434b1a1e4ce6","abstract_canon_sha256":"a4ce221b897b48fe38946b1ea13149762d15cd5f59eb36770b06579c41a615b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:34.531672Z","signature_b64":"73gey5uCsEFL85wEny1ajAzA9OEIZrX4eO6cW4jp96ss597+tb+0pxzsgP4tu/LkHNPSraf0X6RTddNlJNx8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c8524e961bf204e588fadffebba5f2024c7946c02ff9a99dbf870249e80f76d","last_reissued_at":"2026-07-05T08:32:34.531178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:34.531178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Peter Stone, William Yue","submitted_at":"2024-01-04T23:44:35Z","abstract_excerpt":"Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously encountered tasks to augment the current dataset. However, existing deep generative replay methods for continual learning rely on autoregressive models, which suffer from compounding errors in the generated trajectories. In this paper, we propose a simple, scalable, and non-autoregressive method for continual learning in decision-making tasks using a generative mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02576","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/2401.02576/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":"2401.02576","created_at":"2026-07-05T08:32:34.531235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02576v2","created_at":"2026-07-05T08:32:34.531235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02576","created_at":"2026-07-05T08:32:34.531235+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSCSJ2LBX4QE","created_at":"2026-07-05T08:32:34.531235+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSCSJ2LBX4QE4WEP","created_at":"2026-07-05T08:32:34.531235+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSCSJ2LB","created_at":"2026-07-05T08:32:34.531235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27374","citing_title":"World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA","json":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA.json","graph_json":"https://pith.science/api/pith-number/HSCSJ2LBX4QE4WEPVX76XOS7EA/graph.json","events_json":"https://pith.science/api/pith-number/HSCSJ2LBX4QE4WEPVX76XOS7EA/events.json","paper":"https://pith.science/paper/HSCSJ2LB"},"agent_actions":{"view_html":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA","download_json":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA.json","view_paper":"https://pith.science/paper/HSCSJ2LB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02576&json=true","fetch_graph":"https://pith.science/api/pith-number/HSCSJ2LBX4QE4WEPVX76XOS7EA/graph.json","fetch_events":"https://pith.science/api/pith-number/HSCSJ2LBX4QE4WEPVX76XOS7EA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA/action/storage_attestation","attest_author":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA/action/author_attestation","sign_citation":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA/action/citation_signature","submit_replication":"https://pith.science/pith/HSCSJ2LBX4QE4WEPVX76XOS7EA/action/replication_record"}},"created_at":"2026-07-05T08:32:34.531235+00:00","updated_at":"2026-07-05T08:32:34.531235+00:00"}