{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NZY6US7Y6XQFB5K6GQSDMU72QL","short_pith_number":"pith:NZY6US7Y","schema_version":"1.0","canonical_sha256":"6e71ea4bf8f5e050f55e34243653fa82f2ccd2493fdf324302a702a8b2418091","source":{"kind":"arxiv","id":"2505.09925","version":1},"attestation_state":"computed","paper":{"title":"Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bihao Zhan, Jie Zhou, Junsong Li, Liang He, Qianjun Pan, Qin Chen, Xipeng Qiu, Yutao Yang","submitted_at":"2025-05-15T03:22:03Z","abstract_excerpt":"This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This paradigm distinctively addresses two major limitations of traditional continual learning: (1) dynamic model updates using streaming, real-time human-annotated data, rather than static datasets with fixed labels, and (2) the assumption of clean labels, by explicitly handling the noisy feedback common in real-world interactions. To tackle these problems, we propose RiCL, a Reinforced interactive Continual Learning framew"},"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":"2505.09925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-15T03:22:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2ee5bb59cb73d70fc9848d29b82f182ff0042fe53dc031c18ecd94837188331","abstract_canon_sha256":"0f221b88c48e7830c7354975a42368526c16986dacbb1bcbb2dc65f34284a588"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:30.478089Z","signature_b64":"AkU5Tx1QERwOwMQkJA4T6fHtvKOBWM1F9AS5M+bz2Y4hTpy9w+7UVOAMOvzszwTWLXPns0mxD7+CtYNAopOhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e71ea4bf8f5e050f55e34243653fa82f2ccd2493fdf324302a702a8b2418091","last_reissued_at":"2026-07-05T11:03:30.477604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:30.477604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bihao Zhan, Jie Zhou, Junsong Li, Liang He, Qianjun Pan, Qin Chen, Xipeng Qiu, Yutao Yang","submitted_at":"2025-05-15T03:22:03Z","abstract_excerpt":"This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This paradigm distinctively addresses two major limitations of traditional continual learning: (1) dynamic model updates using streaming, real-time human-annotated data, rather than static datasets with fixed labels, and (2) the assumption of clean labels, by explicitly handling the noisy feedback common in real-world interactions. To tackle these problems, we propose RiCL, a Reinforced interactive Continual Learning framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09925","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.09925/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":"2505.09925","created_at":"2026-07-05T11:03:30.477666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09925v1","created_at":"2026-07-05T11:03:30.477666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09925","created_at":"2026-07-05T11:03:30.477666+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZY6US7Y6XQF","created_at":"2026-07-05T11:03:30.477666+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZY6US7Y6XQFB5K6","created_at":"2026-07-05T11:03:30.477666+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZY6US7Y","created_at":"2026-07-05T11:03:30.477666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.17183","citing_title":"LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21678","citing_title":"Agentic Learner with Grow-and-Refine Multimodal Semantic Memory","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL","json":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL.json","graph_json":"https://pith.science/api/pith-number/NZY6US7Y6XQFB5K6GQSDMU72QL/graph.json","events_json":"https://pith.science/api/pith-number/NZY6US7Y6XQFB5K6GQSDMU72QL/events.json","paper":"https://pith.science/paper/NZY6US7Y"},"agent_actions":{"view_html":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL","download_json":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL.json","view_paper":"https://pith.science/paper/NZY6US7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09925&json=true","fetch_graph":"https://pith.science/api/pith-number/NZY6US7Y6XQFB5K6GQSDMU72QL/graph.json","fetch_events":"https://pith.science/api/pith-number/NZY6US7Y6XQFB5K6GQSDMU72QL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL/action/storage_attestation","attest_author":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL/action/author_attestation","sign_citation":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL/action/citation_signature","submit_replication":"https://pith.science/pith/NZY6US7Y6XQFB5K6GQSDMU72QL/action/replication_record"}},"created_at":"2026-07-05T11:03:30.477666+00:00","updated_at":"2026-07-05T11:03:30.477666+00:00"}