{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4A4WGOC55SABQY23WZ7JHIH35F","short_pith_number":"pith:4A4WGOC5","canonical_record":{"source":{"id":"2506.21035","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"5c7edf5d8704bfd33d604f3799eb0dd2dbb4ac3ae3d7e33c0dcd20d8b3b602a0","abstract_canon_sha256":"e9e680cef1bc83c1dfff2e760617013aa7d72bf1950e156c8e02579b8e687984"},"schema_version":"1.0"},"canonical_sha256":"e03963385dec8018635bb67e93a0fbe97c9530c33cafc2780e050e0d7e689c80","source":{"kind":"arxiv","id":"2506.21035","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21035","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21035v5","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21035","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"4A4WGOC55SAB","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"4A4WGOC55SABQY23","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"4A4WGOC5","created_at":"2026-05-22T01:03:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4A4WGOC55SABQY23WZ7JHIH35F","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21035","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"5c7edf5d8704bfd33d604f3799eb0dd2dbb4ac3ae3d7e33c0dcd20d8b3b602a0","abstract_canon_sha256":"e9e680cef1bc83c1dfff2e760617013aa7d72bf1950e156c8e02579b8e687984"},"schema_version":"1.0"},"canonical_sha256":"e03963385dec8018635bb67e93a0fbe97c9530c33cafc2780e050e0d7e689c80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:43.801183Z","signature_b64":"5mbkk0LLBfQAWk/V6k5eFVq4hbc2Gp8vvxYFhEAQtkMJWhHEFmhdl8kOTU8wFtXBW7aWGNpCoOiWaBzrocA1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e03963385dec8018635bb67e93a0fbe97c9530c33cafc2780e050e0d7e689c80","last_reissued_at":"2026-05-22T01:03:43.800301Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:43.800301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21035","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DiB9xlnS1Fqaw80yODb+9E5uglQnq3CbHSbbWKaeHFcPzuVfa7VMn91LFDgir6fRZznKwEVALwYeH6WAoaH2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:41:10.682455Z"},"content_sha256":"77daf65a938d6dc3df158bed267fb8d2de004013a8918ba685fe77362f579569","schema_version":"1.0","event_id":"sha256:77daf65a938d6dc3df158bed267fb8d2de004013a8918ba685fe77362f579569"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4A4WGOC55SABQY23WZ7JHIH35F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chongyang Zhao, Dong Gong, Haodong Lu, Kristen Moore, Lina Yao, Minhui Xue","submitted_at":"2025-06-26T06:19:05Z","abstract_excerpt":"Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting. Existing LoRA-based Mixture-of-Experts (MoE) methods expand capacity by adding isolated new experts while freezing old ones, but still suffer from redundancy, interference, routing ambiguity, and consequent forgetting. We investigate the issues stemming from coarse-grained expert granularity. Coarse-grained experts (e.g., high-rank LoRA) encode low-specialty information, leading to expert duplication/interference and routing degradation/confusion as experts accumulate."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21035","kind":"arxiv","version":5},"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/2506.21035/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":"2026-05-22T01:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"48/t9uyQj2bpf75Ag9LhJAlEAfXQFQfApVdT33FHV8OJzQhx1a9enciOKLdGKhAi9BLh0VASPvUyjXmLTqYUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:41:10.683187Z"},"content_sha256":"a04fa3426b9fca96e93511e49476a48bad35302ca16977669096f9163eb93253","schema_version":"1.0","event_id":"sha256:a04fa3426b9fca96e93511e49476a48bad35302ca16977669096f9163eb93253"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4A4WGOC55SABQY23WZ7JHIH35F/bundle.json","state_url":"https://pith.science/pith/4A4WGOC55SABQY23WZ7JHIH35F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4A4WGOC55SABQY23WZ7JHIH35F/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":"2026-05-29T15:41:10Z","links":{"resolver":"https://pith.science/pith/4A4WGOC55SABQY23WZ7JHIH35F","bundle":"https://pith.science/pith/4A4WGOC55SABQY23WZ7JHIH35F/bundle.json","state":"https://pith.science/pith/4A4WGOC55SABQY23WZ7JHIH35F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4A4WGOC55SABQY23WZ7JHIH35F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4A4WGOC55SABQY23WZ7JHIH35F","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":"e9e680cef1bc83c1dfff2e760617013aa7d72bf1950e156c8e02579b8e687984","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:19:05Z","title_canon_sha256":"5c7edf5d8704bfd33d604f3799eb0dd2dbb4ac3ae3d7e33c0dcd20d8b3b602a0"},"schema_version":"1.0","source":{"id":"2506.21035","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21035","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21035v5","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21035","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"4A4WGOC55SAB","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"4A4WGOC55SABQY23","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"4A4WGOC5","created_at":"2026-05-22T01:03:43Z"}],"graph_snapshots":[{"event_id":"sha256:a04fa3426b9fca96e93511e49476a48bad35302ca16977669096f9163eb93253","target":"graph","created_at":"2026-05-22T01:03:43Z","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/2506.21035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting. Existing LoRA-based Mixture-of-Experts (MoE) methods expand capacity by adding isolated new experts while freezing old ones, but still suffer from redundancy, interference, routing ambiguity, and consequent forgetting. We investigate the issues stemming from coarse-grained expert granularity. Coarse-grained experts (e.g., high-rank LoRA) encode low-specialty information, leading to expert duplication/interference and routing degradation/confusion as experts accumulate.","authors_text":"Chongyang Zhao, Dong Gong, Haodong Lu, Kristen Moore, Lina Yao, Minhui Xue","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:19:05Z","title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21035","kind":"arxiv","version":5},"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":"sha256:77daf65a938d6dc3df158bed267fb8d2de004013a8918ba685fe77362f579569","target":"record","created_at":"2026-05-22T01:03:43Z","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":"e9e680cef1bc83c1dfff2e760617013aa7d72bf1950e156c8e02579b8e687984","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:19:05Z","title_canon_sha256":"5c7edf5d8704bfd33d604f3799eb0dd2dbb4ac3ae3d7e33c0dcd20d8b3b602a0"},"schema_version":"1.0","source":{"id":"2506.21035","kind":"arxiv","version":5}},"canonical_sha256":"e03963385dec8018635bb67e93a0fbe97c9530c33cafc2780e050e0d7e689c80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e03963385dec8018635bb67e93a0fbe97c9530c33cafc2780e050e0d7e689c80","first_computed_at":"2026-05-22T01:03:43.800301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:43.800301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5mbkk0LLBfQAWk/V6k5eFVq4hbc2Gp8vvxYFhEAQtkMJWhHEFmhdl8kOTU8wFtXBW7aWGNpCoOiWaBzrocA1Ag==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:43.801183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21035","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77daf65a938d6dc3df158bed267fb8d2de004013a8918ba685fe77362f579569","sha256:a04fa3426b9fca96e93511e49476a48bad35302ca16977669096f9163eb93253"],"state_sha256":"f18a1478408e01f43a3d9aa64efa6e7d76d4373227868c8f2fbd637c5e61295b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZ26DnjJxNgfAgalyR9VA0LzxNkmAKJAjDz+JWZgj6cUM3S/niisNMPdS2QiBlK59t6Q6E2H3KYg4AB9HMeoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:41:10.686866Z","bundle_sha256":"eabf044cee8b7e3a9e17ba9a08c2910850fc806bcb6a4067d1108c248676acff"}}