{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3I4A2CE7OJK6DESR6OEZXAIM2B","short_pith_number":"pith:3I4A2CE7","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"},"canonical_sha256":"da380d089f7255e19251f3899b810cd073079e079c52ca87a2d06ddf6f44ab38","source":{"kind":"arxiv","id":"2508.09510","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09510","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09510v1","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09510","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"3I4A2CE7OJK6","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"3I4A2CE7OJK6DESR","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"3I4A2CE7","created_at":"2026-07-05T11:53:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3I4A2CE7OJK6DESR6OEZXAIM2B","target":"record","payload":{"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"},"canonical_sha256":"da380d089f7255e19251f3899b810cd073079e079c52ca87a2d06ddf6f44ab38","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"},"source_kind":"arxiv","source_id":"2508.09510","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8M5EPXrttrsZVCgGnLpm5QL1eqrAMBa+DSb0cqHF7q5oMMLdOIi2miffdrRFnREyxANzegkgQmXHJ65SQHfWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:22.444123Z"},"content_sha256":"822576f84bed0a14ab979e3845fdce66312d7c2bd4128fe2fb7b16395b70a30d","schema_version":"1.0","event_id":"sha256:822576f84bed0a14ab979e3845fdce66312d7c2bd4128fe2fb7b16395b70a30d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3I4A2CE7OJK6DESR6OEZXAIM2B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lptynapx1NsJm8UVMl0LC0xmJB6CNVlEN+Xb4Ka7+pViclFkBlYRgPa1LbeSavbqQ5K15HzORLP6eNGxRq1vAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:22.444710Z"},"content_sha256":"650df2936253a9910d7a38a683b6f438729d8662f8780fe127aeeb4c6d5cc5cb","schema_version":"1.0","event_id":"sha256:650df2936253a9910d7a38a683b6f438729d8662f8780fe127aeeb4c6d5cc5cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/bundle.json","state_url":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T01:45:22Z","links":{"resolver":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B","bundle":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/bundle.json","state":"https://pith.science/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3I4A2CE7OJK6DESR6OEZXAIM2B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3I4A2CE7OJK6DESR6OEZXAIM2B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8035d441fcce4cfda6e9a07728f80e9907a13a08892e1bfd9cb7d09b58574532","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T05:45:58Z","title_canon_sha256":"9fb8fdde03a3c8c1d1dd62cf454f4655a669737701890c59b42ee7d56a237ae0"},"schema_version":"1.0","source":{"id":"2508.09510","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09510","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09510v1","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09510","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"3I4A2CE7OJK6","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"3I4A2CE7OJK6DESR","created_at":"2026-07-05T11:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"3I4A2CE7","created_at":"2026-07-05T11:53:16Z"}],"graph_snapshots":[{"event_id":"sha256:650df2936253a9910d7a38a683b6f438729d8662f8780fe127aeeb4c6d5cc5cb","target":"graph","created_at":"2026-07-05T11:53:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.09510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Iing Muttakhiroh, Thomas Fevens","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T05:45:58Z","title":"Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09510","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:822576f84bed0a14ab979e3845fdce66312d7c2bd4128fe2fb7b16395b70a30d","target":"record","created_at":"2026-07-05T11:53:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8035d441fcce4cfda6e9a07728f80e9907a13a08892e1bfd9cb7d09b58574532","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T05:45:58Z","title_canon_sha256":"9fb8fdde03a3c8c1d1dd62cf454f4655a669737701890c59b42ee7d56a237ae0"},"schema_version":"1.0","source":{"id":"2508.09510","kind":"arxiv","version":1}},"canonical_sha256":"da380d089f7255e19251f3899b810cd073079e079c52ca87a2d06ddf6f44ab38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da380d089f7255e19251f3899b810cd073079e079c52ca87a2d06ddf6f44ab38","first_computed_at":"2026-07-05T11:53:16.332942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:16.332942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xf3Lkj54Y3JfeK0aeq4+QBp14gbE637HgnTzMDvqOgXYdFQxuKRJRNrOtvhofobaLEJI6qH0CTSCR+pc3ZkoCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:16.333446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09510","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:822576f84bed0a14ab979e3845fdce66312d7c2bd4128fe2fb7b16395b70a30d","sha256:650df2936253a9910d7a38a683b6f438729d8662f8780fe127aeeb4c6d5cc5cb"],"state_sha256":"9b112983709cf35bd02ff6614ce5db7ac59691d8dff6b24490132ad0fac9623b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXfhYYsfSgKRw9sWPGFmThHxCfTJnP8k2vTJLd9ss58XwTPG8zD2sxYgsw1APMapUOmQgF3Qb6e6IB3YbUe6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:45:22.449433Z","bundle_sha256":"459f9eb4ee9659fb6fb8cd1c561cee763a5162cfd295ed8a5125de85bdac1f2a"}}