{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2ANX2XWHJJ3VLJAT7YU7T34F5I","short_pith_number":"pith:2ANX2XWH","schema_version":"1.0","canonical_sha256":"d01b7d5ec74a7755a413fe29f9ef85ea028b27951e927fe3f22afc1dffb6e1cb","source":{"kind":"arxiv","id":"2607.22556","version":1},"attestation_state":"computed","paper":{"title":"MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chen Zhao, Dong Li, Haifeng Chen, Wei Cheng, Xintao Wu, Xujiang Zhao, Yanchi Liu, Zhengzhang Chen, Zhong Chen","submitted_at":"2026-05-20T03:03:04Z","abstract_excerpt":"Continual learning (CL) is essential for small language models (SLMs) to adapt to evolving real-world needs in resource-constrained deployments. However, directly updating their limited parameter space causes catastrophic forgetting. While memory-based methods naturally address this by decoupling knowledge retention from parameters, existing approaches designed for large language models (LLMs) rely on abundant storage and strong in-context reasoning that SLMs lack. To address these challenges, we propose MIITA, a Memory-Induced Inference-Time Adaptation framework for supervised CL under constr"},"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":"2607.22556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T03:03:04Z","cross_cats_sorted":[],"title_canon_sha256":"2663d6f3082b534128beb3b69f423ba4315f96d0f3f9362442c9c2b96fc725e4","abstract_canon_sha256":"8b8ec7ed9dfd00ef8565b2e878fff0f2335a406c958c1243c888ea87e69f168c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:42.066028Z","signature_b64":"4ARTGInZCUUEhze91/r6JhZn38DmfeWSnreRVDJTSBDqZARAiGHyMA88fIXuRK1xffcHshfWiLBVFp9DnNtTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d01b7d5ec74a7755a413fe29f9ef85ea028b27951e927fe3f22afc1dffb6e1cb","last_reissued_at":"2026-07-28T00:21:42.065053Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:42.065053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chen Zhao, Dong Li, Haifeng Chen, Wei Cheng, Xintao Wu, Xujiang Zhao, Yanchi Liu, Zhengzhang Chen, Zhong Chen","submitted_at":"2026-05-20T03:03:04Z","abstract_excerpt":"Continual learning (CL) is essential for small language models (SLMs) to adapt to evolving real-world needs in resource-constrained deployments. However, directly updating their limited parameter space causes catastrophic forgetting. While memory-based methods naturally address this by decoupling knowledge retention from parameters, existing approaches designed for large language models (LLMs) rely on abundant storage and strong in-context reasoning that SLMs lack. To address these challenges, we propose MIITA, a Memory-Induced Inference-Time Adaptation framework for supervised CL under constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22556","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/2607.22556/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":"2607.22556","created_at":"2026-07-28T00:21:42.065527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22556v1","created_at":"2026-07-28T00:21:42.065527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22556","created_at":"2026-07-28T00:21:42.065527+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ANX2XWHJJ3V","created_at":"2026-07-28T00:21:42.065527+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ANX2XWHJJ3VLJAT","created_at":"2026-07-28T00:21:42.065527+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ANX2XWH","created_at":"2026-07-28T00:21:42.065527+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/2ANX2XWHJJ3VLJAT7YU7T34F5I","json":"https://pith.science/pith/2ANX2XWHJJ3VLJAT7YU7T34F5I.json","graph_json":"https://pith.science/api/pith-number/2ANX2XWHJJ3VLJAT7YU7T34F5I/graph.json","events_json":"https://pith.science/api/pith-number/2ANX2XWHJJ3VLJAT7YU7T34F5I/events.json","paper":"https://pith.science/paper/2ANX2XWH"},"agent_actions":{"view_html":"https://pith.science/pith/2ANX2XWHJJ3VLJAT7YU7T34F5I","download_json":"https://pith.science/pith/2ANX2XWHJJ3VLJAT7YU7T34F5I.json","view_paper":"https://pith.science/paper/2ANX2XWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22556&json=true","fetch_graph":"https://pith.science/api/pith-number/2ANX2XWHJJ3VLJAT7YU7T34F5I/graph.json","fetch_events":"https://pith.science/api/pith-number/2ANX2XWHJJ3VLJAT7YU7T34F5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ANX2XWHJJ3VLJAT7YU7T34F5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ANX2XWHJJ3VLJAT7YU7T34F5I/action/storage_attestation","attest_author":"https://pith.science/pith/2ANX2XWHJJ3VLJAT7YU7T34F5I/action/author_attestation","sign_citation":"https://pith.science/pith/2ANX2XWHJJ3VLJAT7YU7T34F5I/action/citation_signature","submit_replication":"https://pith.science/pith/2ANX2XWHJJ3VLJAT7YU7T34F5I/action/replication_record"}},"created_at":"2026-07-28T00:21:42.065527+00:00","updated_at":"2026-07-28T00:21:42.065527+00:00"}