{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZIFSZH6H67HJXGLMQGQHEU4IMQ","short_pith_number":"pith:ZIFSZH6H","canonical_record":{"source":{"id":"2503.01887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T03:39:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01467622f0067520030e5b7cc21ee5ff97a606dbf1adcaeb1c45dca0351e743a","abstract_canon_sha256":"e55629aed94da36908bd7649db3e07abb80e09c476d545ccbc013334653811f6"},"schema_version":"1.0"},"canonical_sha256":"ca0b2c9fc7f7ce9b996c81a07253886433fcf72e09a81b0290f4831ab699b349","source":{"kind":"arxiv","id":"2503.01887","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01887","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01887v1","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01887","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZIFSZH6H67HJ","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZIFSZH6H67HJXGLM","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZIFSZH6H","created_at":"2026-07-05T10:23:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZIFSZH6H67HJXGLMQGQHEU4IMQ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.01887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T03:39:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01467622f0067520030e5b7cc21ee5ff97a606dbf1adcaeb1c45dca0351e743a","abstract_canon_sha256":"e55629aed94da36908bd7649db3e07abb80e09c476d545ccbc013334653811f6"},"schema_version":"1.0"},"canonical_sha256":"ca0b2c9fc7f7ce9b996c81a07253886433fcf72e09a81b0290f4831ab699b349","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:31.766899Z","signature_b64":"1trUGU87oqFcsCR4Il67qj4zMApjW6bjO8HUeefleNkZsC/QaldNFD4ZLFJHuRomi13N+uzocInTuHIYymTxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca0b2c9fc7f7ce9b996c81a07253886433fcf72e09a81b0290f4831ab699b349","last_reissued_at":"2026-07-05T10:23:31.766260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:31.766260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.01887","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":"2026-07-05T10:23:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yNjxQwQlG/yhTQ0cazRpHOD5f1pp4L8/XZx1TFYFse5QdH+NMxKCvgthCbCi1xjZfu7PvHNM6X8lxa24cDF8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:09:25.901859Z"},"content_sha256":"ff114237b34ecd53d18f5223db44fad2bc3d7be7b5c23bd1bc925a3a9d8b4a7b","schema_version":"1.0","event_id":"sha256:ff114237b34ecd53d18f5223db44fad2bc3d7be7b5c23bd1bc925a3a9d8b4a7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZIFSZH6H67HJXGLMQGQHEU4IMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Continue Learning Meets Multimodal Large Language Model: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hao Tang, Yukang Huo","submitted_at":"2025-02-27T03:39:10Z","abstract_excerpt":"Recent advancements in Artificial Intelligence have led to the development of Multimodal Large Language Models (MLLMs). However, adapting these pre-trained models to dynamic data distributions and various tasks efficiently remains a challenge. Fine-tuning MLLMs for specific tasks often causes performance degradation in the model's prior knowledge domain, a problem known as 'Catastrophic Forgetting'. While this issue has been well-studied in the Continual Learning (CL) community, it presents new challenges for MLLMs. This review paper, the first of its kind in MLLM continual learning, presents "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01887","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/2503.01887/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":"2026-07-05T10:23:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xzun5ezXew1OUOhr/2vJ224aNImra0opnjttvSmkoyjTfPmOPYUS9b5jPb5XI1ZKK8fuuYnylKvDjQKSXoqwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:09:25.902233Z"},"content_sha256":"6bd85ac587e9cc13a819daeb4d8b416fe69f7f621454670e7b617b063befe58c","schema_version":"1.0","event_id":"sha256:6bd85ac587e9cc13a819daeb4d8b416fe69f7f621454670e7b617b063befe58c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZIFSZH6H67HJXGLMQGQHEU4IMQ/bundle.json","state_url":"https://pith.science/pith/ZIFSZH6H67HJXGLMQGQHEU4IMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZIFSZH6H67HJXGLMQGQHEU4IMQ/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":"2026-07-06T09:09:25Z","links":{"resolver":"https://pith.science/pith/ZIFSZH6H67HJXGLMQGQHEU4IMQ","bundle":"https://pith.science/pith/ZIFSZH6H67HJXGLMQGQHEU4IMQ/bundle.json","state":"https://pith.science/pith/ZIFSZH6H67HJXGLMQGQHEU4IMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZIFSZH6H67HJXGLMQGQHEU4IMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZIFSZH6H67HJXGLMQGQHEU4IMQ","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":"e55629aed94da36908bd7649db3e07abb80e09c476d545ccbc013334653811f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T03:39:10Z","title_canon_sha256":"01467622f0067520030e5b7cc21ee5ff97a606dbf1adcaeb1c45dca0351e743a"},"schema_version":"1.0","source":{"id":"2503.01887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01887","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01887v1","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01887","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZIFSZH6H67HJ","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZIFSZH6H67HJXGLM","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZIFSZH6H","created_at":"2026-07-05T10:23:31Z"}],"graph_snapshots":[{"event_id":"sha256:6bd85ac587e9cc13a819daeb4d8b416fe69f7f621454670e7b617b063befe58c","target":"graph","created_at":"2026-07-05T10:23:31Z","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/2503.01887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Artificial Intelligence have led to the development of Multimodal Large Language Models (MLLMs). However, adapting these pre-trained models to dynamic data distributions and various tasks efficiently remains a challenge. Fine-tuning MLLMs for specific tasks often causes performance degradation in the model's prior knowledge domain, a problem known as 'Catastrophic Forgetting'. While this issue has been well-studied in the Continual Learning (CL) community, it presents new challenges for MLLMs. This review paper, the first of its kind in MLLM continual learning, presents ","authors_text":"Hao Tang, Yukang Huo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T03:39:10Z","title":"When Continue Learning Meets Multimodal Large Language Model: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01887","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:ff114237b34ecd53d18f5223db44fad2bc3d7be7b5c23bd1bc925a3a9d8b4a7b","target":"record","created_at":"2026-07-05T10:23:31Z","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":"e55629aed94da36908bd7649db3e07abb80e09c476d545ccbc013334653811f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T03:39:10Z","title_canon_sha256":"01467622f0067520030e5b7cc21ee5ff97a606dbf1adcaeb1c45dca0351e743a"},"schema_version":"1.0","source":{"id":"2503.01887","kind":"arxiv","version":1}},"canonical_sha256":"ca0b2c9fc7f7ce9b996c81a07253886433fcf72e09a81b0290f4831ab699b349","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca0b2c9fc7f7ce9b996c81a07253886433fcf72e09a81b0290f4831ab699b349","first_computed_at":"2026-07-05T10:23:31.766260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:31.766260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1trUGU87oqFcsCR4Il67qj4zMApjW6bjO8HUeefleNkZsC/QaldNFD4ZLFJHuRomi13N+uzocInTuHIYymTxBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:31.766899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff114237b34ecd53d18f5223db44fad2bc3d7be7b5c23bd1bc925a3a9d8b4a7b","sha256:6bd85ac587e9cc13a819daeb4d8b416fe69f7f621454670e7b617b063befe58c"],"state_sha256":"fa5f4f354882c508450e4117307bfb6a6ff3351cfeddc7d817e1d9e48907dbbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8K6Zc2/qlEOh2eklrvFf0hdu5KbJbcz7HJ4uNLcxkMbvPDux/VQherb8bsUgiHaLBRMxj14BxOb5IzDiVgrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T09:09:25.904157Z","bundle_sha256":"57dee4741fd7077aed44abaec543ac689a063141e6c31a83f4f1288f957a78bb"}}