{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KN6ED57SJL3BPNTR7BKWUJ4ARX","short_pith_number":"pith:KN6ED57S","canonical_record":{"source":{"id":"2509.06219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-07T21:49:43Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e5aa7bef9acc93dfc5c9c58814b824f4c1a2ebcab9dd696d2fe31a612d5f4e8f","abstract_canon_sha256":"4977d1de30cf7fd954e4bae12b5c52a8e418dfcf70faf9fbea891c21f4da7e4a"},"schema_version":"1.0"},"canonical_sha256":"537c41f7f24af617b671f8556a27808dd6e4a0a21c957bff89f7007293df5142","source":{"kind":"arxiv","id":"2509.06219","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06219","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06219v1","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06219","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"KN6ED57SJL3B","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"KN6ED57SJL3BPNTR","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"KN6ED57S","created_at":"2026-07-05T12:06:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KN6ED57SJL3BPNTR7BKWUJ4ARX","target":"record","payload":{"canonical_record":{"source":{"id":"2509.06219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-07T21:49:43Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e5aa7bef9acc93dfc5c9c58814b824f4c1a2ebcab9dd696d2fe31a612d5f4e8f","abstract_canon_sha256":"4977d1de30cf7fd954e4bae12b5c52a8e418dfcf70faf9fbea891c21f4da7e4a"},"schema_version":"1.0"},"canonical_sha256":"537c41f7f24af617b671f8556a27808dd6e4a0a21c957bff89f7007293df5142","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:31.990164Z","signature_b64":"rQj2wPrNfQtP1hLO7XqPDr48YdvaSCyNpNcgk1Dfw2EjzXq9KGjtiGIzRe0P/g7VQ9KOCGHzSSrTANSDqDKaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"537c41f7f24af617b671f8556a27808dd6e4a0a21c957bff89f7007293df5142","last_reissued_at":"2026-07-05T12:06:31.989609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:31.989609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.06219","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":"2026-07-05T12:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FlAzDcMutEoUyzNBzqOb1z8PQpxM7P2laLH3ftph/kwaF0KS05Co2J/sW52uE1RvoLSrVFnpivKbH80XvoZ+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T08:57:37.722050Z"},"content_sha256":"ec8cdadcd6c96fe2d1678cf15bc22bd685c9e191ec8008ffcb199998aa95c516","schema_version":"1.0","event_id":"sha256:ec8cdadcd6c96fe2d1678cf15bc22bd685c9e191ec8008ffcb199998aa95c516"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KN6ED57SJL3BPNTR7BKWUJ4ARX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.LG","authors_text":"Baojing Liu, Haochen You","submitted_at":"2025-09-07T21:49:43Z","abstract_excerpt":"Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like catastrophic forgetting, distribution bias, memory limits, and weak generalization. We propose MCIGLE, a novel framework that addresses these issues by extracting and aligning multimodal graph features and applying Concatenated Recursive Least Squares for effective knowledge retention. Through multi-channel processing, MCIGLE balances accuracy and memory prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06219","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/2509.06219/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":"2026-07-05T12:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ctsRO7lxT6dqaqk7w7k5pJas8CemzV4ierwXzmM9OPhtTRRaOiDk+clO+P4PEfWTcXo6ld5fIZXlS77LbTE6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T08:57:37.722834Z"},"content_sha256":"5057f92289e08394bfcb7745e44fcc92a2d7cdb04e1a94541c72bf44cabd75db","schema_version":"1.0","event_id":"sha256:5057f92289e08394bfcb7745e44fcc92a2d7cdb04e1a94541c72bf44cabd75db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KN6ED57SJL3BPNTR7BKWUJ4ARX/bundle.json","state_url":"https://pith.science/pith/KN6ED57SJL3BPNTR7BKWUJ4ARX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KN6ED57SJL3BPNTR7BKWUJ4ARX/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":"2026-08-23T08:57:37Z","links":{"resolver":"https://pith.science/pith/KN6ED57SJL3BPNTR7BKWUJ4ARX","bundle":"https://pith.science/pith/KN6ED57SJL3BPNTR7BKWUJ4ARX/bundle.json","state":"https://pith.science/pith/KN6ED57SJL3BPNTR7BKWUJ4ARX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KN6ED57SJL3BPNTR7BKWUJ4ARX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KN6ED57SJL3BPNTR7BKWUJ4ARX","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":"4977d1de30cf7fd954e4bae12b5c52a8e418dfcf70faf9fbea891c21f4da7e4a","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-07T21:49:43Z","title_canon_sha256":"e5aa7bef9acc93dfc5c9c58814b824f4c1a2ebcab9dd696d2fe31a612d5f4e8f"},"schema_version":"1.0","source":{"id":"2509.06219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06219","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06219v1","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06219","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"KN6ED57SJL3B","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"KN6ED57SJL3BPNTR","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"KN6ED57S","created_at":"2026-07-05T12:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:5057f92289e08394bfcb7745e44fcc92a2d7cdb04e1a94541c72bf44cabd75db","target":"graph","created_at":"2026-07-05T12:06:31Z","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/2509.06219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like catastrophic forgetting, distribution bias, memory limits, and weak generalization. We propose MCIGLE, a novel framework that addresses these issues by extracting and aligning multimodal graph features and applying Concatenated Recursive Least Squares for effective knowledge retention. Through multi-channel processing, MCIGLE balances accuracy and memory prese","authors_text":"Baojing Liu, Haochen You","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-07T21:49:43Z","title":"MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06219","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:ec8cdadcd6c96fe2d1678cf15bc22bd685c9e191ec8008ffcb199998aa95c516","target":"record","created_at":"2026-07-05T12:06:31Z","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":"4977d1de30cf7fd954e4bae12b5c52a8e418dfcf70faf9fbea891c21f4da7e4a","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-07T21:49:43Z","title_canon_sha256":"e5aa7bef9acc93dfc5c9c58814b824f4c1a2ebcab9dd696d2fe31a612d5f4e8f"},"schema_version":"1.0","source":{"id":"2509.06219","kind":"arxiv","version":1}},"canonical_sha256":"537c41f7f24af617b671f8556a27808dd6e4a0a21c957bff89f7007293df5142","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"537c41f7f24af617b671f8556a27808dd6e4a0a21c957bff89f7007293df5142","first_computed_at":"2026-07-05T12:06:31.989609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:31.989609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rQj2wPrNfQtP1hLO7XqPDr48YdvaSCyNpNcgk1Dfw2EjzXq9KGjtiGIzRe0P/g7VQ9KOCGHzSSrTANSDqDKaDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:31.990164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec8cdadcd6c96fe2d1678cf15bc22bd685c9e191ec8008ffcb199998aa95c516","sha256:5057f92289e08394bfcb7745e44fcc92a2d7cdb04e1a94541c72bf44cabd75db"],"state_sha256":"8e31adf684f87cc795129516d8de28ed9878e753d64546fa0fab234929f7dd90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xyDtcobwrKiTdWkfaTJ9OpdaURSrKVARD5z5miU4MCuUgNbvl/0kEMe1a2XcT6qfRxvEAFDjlWkEu5RG5LJLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T08:57:37.728314Z","bundle_sha256":"3268aaecec6f84f4e2f264b521d0bb0c5d7e1bed386cf2d34ec80343eaae048e"}}