{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5PSRNSJOVKHOEEYCBHRNBWV7LV","short_pith_number":"pith:5PSRNSJO","schema_version":"1.0","canonical_sha256":"ebe516c92eaa8ee2130209e2d0dabf5d6cfd8f5ddfaec46e0db3a75c3fa4f6b0","source":{"kind":"arxiv","id":"2605.14938","version":1},"attestation_state":"computed","paper":{"title":"Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chao Ma, Shanyan Guan, Weijia Zhang, Wei Li, Xuanming Shang, Yanhao Ge, Yuehao Liu","submitted_at":"2026-05-14T15:13:24Z","abstract_excerpt":"Continual learning in multimodal large language models (MLLMs) aims to sequentially acquire knowledge while mitigating catastrophic forgetting, yet existing methods face inherent limitations: architecture-based approaches incur additional computational overhead and often generalize poorly to new tasks, rehearsal-based methods rely on storing historical data, raising privacy and storage concerns, and conventional regularization-based strategies alone are insufficient to fully prevent parameter interference. We propose Octopus, a two-stage continual learning framework based on History-Free Gradi"},"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":"2605.14938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T15:13:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1623798bdbfbb00f9159baba6c326c11f2487ecd4a366031084595a73f15f977","abstract_canon_sha256":"efc0254434c86735152f7c7ec0fb6cb32237334fc60d7918a85d2ba20f9335f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:55.499587Z","signature_b64":"ZXGC6Zc9kE/M34fBvlVSbWktPyh3KGKfgrg1RpXDzuCosEY5ctslOxF7JUw+PB0fuRiRr/VbpxngaRvlhs6KBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebe516c92eaa8ee2130209e2d0dabf5d6cfd8f5ddfaec46e0db3a75c3fa4f6b0","last_reissued_at":"2026-05-17T23:38:55.498895Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:55.498895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chao Ma, Shanyan Guan, Weijia Zhang, Wei Li, Xuanming Shang, Yanhao Ge, Yuehao Liu","submitted_at":"2026-05-14T15:13:24Z","abstract_excerpt":"Continual learning in multimodal large language models (MLLMs) aims to sequentially acquire knowledge while mitigating catastrophic forgetting, yet existing methods face inherent limitations: architecture-based approaches incur additional computational overhead and often generalize poorly to new tasks, rehearsal-based methods rely on storing historical data, raising privacy and storage concerns, and conventional regularization-based strategies alone are insufficient to fully prevent parameter interference. We propose Octopus, a two-stage continual learning framework based on History-Free Gradi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14938","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":""},"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":"2605.14938","created_at":"2026-05-17T23:38:55.499012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14938v1","created_at":"2026-05-17T23:38:55.499012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14938","created_at":"2026-05-17T23:38:55.499012+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PSRNSJOVKHO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PSRNSJOVKHOEEYC","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PSRNSJO","created_at":"2026-05-18T12:33:37.589309+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/5PSRNSJOVKHOEEYCBHRNBWV7LV","json":"https://pith.science/pith/5PSRNSJOVKHOEEYCBHRNBWV7LV.json","graph_json":"https://pith.science/api/pith-number/5PSRNSJOVKHOEEYCBHRNBWV7LV/graph.json","events_json":"https://pith.science/api/pith-number/5PSRNSJOVKHOEEYCBHRNBWV7LV/events.json","paper":"https://pith.science/paper/2605.14938"},"agent_actions":{"view_html":"https://pith.science/pith/5PSRNSJOVKHOEEYCBHRNBWV7LV","download_json":"https://pith.science/pith/5PSRNSJOVKHOEEYCBHRNBWV7LV.json","view_paper":"https://pith.science/paper/2605.14938","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14938&json=true","fetch_graph":"https://pith.science/api/pith-number/5PSRNSJOVKHOEEYCBHRNBWV7LV/graph.json","fetch_events":"https://pith.science/api/pith-number/5PSRNSJOVKHOEEYCBHRNBWV7LV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PSRNSJOVKHOEEYCBHRNBWV7LV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PSRNSJOVKHOEEYCBHRNBWV7LV/action/storage_attestation","attest_author":"https://pith.science/pith/5PSRNSJOVKHOEEYCBHRNBWV7LV/action/author_attestation","sign_citation":"https://pith.science/pith/5PSRNSJOVKHOEEYCBHRNBWV7LV/action/citation_signature","submit_replication":"https://pith.science/pith/5PSRNSJOVKHOEEYCBHRNBWV7LV/action/replication_record"}},"created_at":"2026-05-17T23:38:55.499012+00:00","updated_at":"2026-05-17T23:38:55.499012+00:00"}