{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B4YXC4YOSMZL35S66N7QDK57PQ","short_pith_number":"pith:B4YXC4YO","schema_version":"1.0","canonical_sha256":"0f3171730e9332bdf65ef37f01abbf7c04d0e16dad3cfa9f76d53a3a0d2ffd82","source":{"kind":"arxiv","id":"2410.10341","version":2},"attestation_state":"computed","paper":{"title":"Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bing Liu, Chaoxi Niu, Guansong Pang, Ling Chen","submitted_at":"2024-10-14T09:54:20Z","abstract_excerpt":"Class-incremental learning (CIL) aims to continually learn a sequence of tasks, with each task consisting of a set of unique classes. Graph CIL (GCIL) follows the same setting but needs to deal with graph tasks (e.g., node classification in a graph). The key characteristic of CIL lies in the absence of task identifiers (IDs) during inference, which causes a significant challenge in separating classes from different tasks (i.e., inter-task class separation). Being able to accurately predict the task IDs can help address this issue, but it is a challenging problem. In this paper, we show theoret"},"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":"2410.10341","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T09:54:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ce103fabba3fb9af6d8f8e813548295cd0ee212273145262ac9a725b0033385f","abstract_canon_sha256":"5afc65bb76b7eed0ac6116261a10e68fb44eb03e4474cdc34f4aee42126c3ed3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:06.144053Z","signature_b64":"IwVTw1sHf/nCOumys5RGS9+OK3UK6y9zN8d2yQrxwkRPkn2fe2osfoCeF0SHpsUG5WK4icskFyGKP2CrpKqSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f3171730e9332bdf65ef37f01abbf7c04d0e16dad3cfa9f76d53a3a0d2ffd82","last_reissued_at":"2026-07-05T09:27:06.143583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:06.143583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bing Liu, Chaoxi Niu, Guansong Pang, Ling Chen","submitted_at":"2024-10-14T09:54:20Z","abstract_excerpt":"Class-incremental learning (CIL) aims to continually learn a sequence of tasks, with each task consisting of a set of unique classes. Graph CIL (GCIL) follows the same setting but needs to deal with graph tasks (e.g., node classification in a graph). The key characteristic of CIL lies in the absence of task identifiers (IDs) during inference, which causes a significant challenge in separating classes from different tasks (i.e., inter-task class separation). Being able to accurately predict the task IDs can help address this issue, but it is a challenging problem. In this paper, we show theoret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10341","kind":"arxiv","version":2},"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/2410.10341/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.10341","created_at":"2026-07-05T09:27:06.143644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10341v2","created_at":"2026-07-05T09:27:06.143644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10341","created_at":"2026-07-05T09:27:06.143644+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4YXC4YOSMZL","created_at":"2026-07-05T09:27:06.143644+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4YXC4YOSMZL35S6","created_at":"2026-07-05T09:27:06.143644+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4YXC4YO","created_at":"2026-07-05T09:27:06.143644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15116","citing_title":"Graph Foundation Models: A Comprehensive Survey","ref_index":239,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ","json":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ.json","graph_json":"https://pith.science/api/pith-number/B4YXC4YOSMZL35S66N7QDK57PQ/graph.json","events_json":"https://pith.science/api/pith-number/B4YXC4YOSMZL35S66N7QDK57PQ/events.json","paper":"https://pith.science/paper/B4YXC4YO"},"agent_actions":{"view_html":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ","download_json":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ.json","view_paper":"https://pith.science/paper/B4YXC4YO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10341&json=true","fetch_graph":"https://pith.science/api/pith-number/B4YXC4YOSMZL35S66N7QDK57PQ/graph.json","fetch_events":"https://pith.science/api/pith-number/B4YXC4YOSMZL35S66N7QDK57PQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ/action/storage_attestation","attest_author":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ/action/author_attestation","sign_citation":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ/action/citation_signature","submit_replication":"https://pith.science/pith/B4YXC4YOSMZL35S66N7QDK57PQ/action/replication_record"}},"created_at":"2026-07-05T09:27:06.143644+00:00","updated_at":"2026-07-05T09:27:06.143644+00:00"}