{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3I4A2CE7OJK6DESR6OEZXAIM2B","short_pith_number":"pith:3I4A2CE7","schema_version":"1.0","canonical_sha256":"da380d089f7255e19251f3899b810cd073079e079c52ca87a2d06ddf6f44ab38","source":{"kind":"arxiv","id":"2508.09510","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Iing Muttakhiroh, Thomas Fevens","submitted_at":"2025-08-13T05:45:58Z","abstract_excerpt":"Despite the significant advancements in Large Language Models (LLMs), catastrophic forgetting remains a substantial challenge, where models lose previously acquired knowledge upon learning new information. Continual learning (CL) strategies have emerged as a potential solution to this problem, with replay-based techniques demonstrating superior performance in preserving learned knowledge. In this context, we introduce Gauss-Tin, a novel approach that integrates the replay strategy with a Gaussian mixture model to enhance the quality of sample selection during training, supplemented by instruct"},"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":"2508.09510","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T05:45:58Z","cross_cats_sorted":[],"title_canon_sha256":"9fb8fdde03a3c8c1d1dd62cf454f4655a669737701890c59b42ee7d56a237ae0","abstract_canon_sha256":"8035d441fcce4cfda6e9a07728f80e9907a13a08892e1bfd9cb7d09b58574532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:16.333446Z","signature_b64":"xf3Lkj54Y3JfeK0aeq4+QBp14gbE637HgnTzMDvqOgXYdFQxuKRJRNrOtvhofobaLEJI6qH0CTSCR+pc3ZkoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da380d089f7255e19251f3899b810cd073079e079c52ca87a2d06ddf6f44ab38","last_reissued_at":"2026-07-05T11:53:16.332942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:16.332942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Iing Muttakhiroh, Thomas Fevens","submitted_at":"2025-08-13T05:45:58Z","abstract_excerpt":"Despite the significant advancements in Large Language Models (LLMs), catastrophic forgetting remains a substantial challenge, where models lose previously acquired knowledge upon learning new information. Continual learning (CL) strategies have emerged as a potential solution to this problem, with replay-based techniques demonstrating superior performance in preserving learned knowledge. In this context, we introduce Gauss-Tin, a novel approach that integrates the replay strategy with a Gaussian mixture model to enhance the quality of sample selection during training, supplemented by instruct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09510","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/2508.09510/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":"2508.09510","created_at":"2026-07-05T11:53:16.333002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09510v1","created_at":"2026-07-05T11:53:16.333002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09510","created_at":"2026-07-05T11:53:16.333002+00:00"},{"alias_kind":"pith_short_12","alias_value":"3I4A2CE7OJK6","created_at":"2026-07-05T11:53:16.333002+00:00"},{"alias_kind":"pith_short_16","alias_value":"3I4A2CE7OJK6DESR","created_at":"2026-07-05T11:53:16.333002+00:00"},{"alias_kind":"pith_short_8","alias_value":"3I4A2CE7","created_at":"2026-07-05T11:53:16.333002+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/3I4A2CE7OJK6DESR6OEZXAIM2B","json":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B.json","graph_json":"https://pith.science/api/pith-number/3I4A2CE7OJK6DESR6OEZXAIM2B/graph.json","events_json":"https://pith.science/api/pith-number/3I4A2CE7OJK6DESR6OEZXAIM2B/events.json","paper":"https://pith.science/paper/3I4A2CE7"},"agent_actions":{"view_html":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B","download_json":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B.json","view_paper":"https://pith.science/paper/3I4A2CE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09510&json=true","fetch_graph":"https://pith.science/api/pith-number/3I4A2CE7OJK6DESR6OEZXAIM2B/graph.json","fetch_events":"https://pith.science/api/pith-number/3I4A2CE7OJK6DESR6OEZXAIM2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/action/storage_attestation","attest_author":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/action/author_attestation","sign_citation":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/action/citation_signature","submit_replication":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/action/replication_record"}},"created_at":"2026-07-05T11:53:16.333002+00:00","updated_at":"2026-07-05T11:53:16.333002+00:00"}