{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_3705f05b1bdbf666002d341c8d3fa507bf8b1f37bf09f15033ca4034165fdb16","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_3705f05b1bdbf666002d341c8d3fa507bf8b1f37bf09f15033ca4034165fdb16","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"a3fb27948aa6084c9aea8c833e5ec17d4f61892fe454635c52341da1a6c350c3","published":"Mon, 13 Jul 2026 00:00:00 -0400","receipt_hash":"a3fb27948aa6084c9aea8c833e5ec17d4f61892fe454635c52341da1a6c350c3","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"a3fb27948aa6084c9aea8c833e5ec17d4f61892fe454635c52341da1a6c350c3","observed_at":"2026-07-13T04:43:08.394955Z","parent_run_hash":"900c1c934245e788564e199a9619f2dc36ec91d9804ddd9c6a40fb42c8a1e1c0","published":"Mon, 13 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2607.08784v1 Announce Type: cross \nAbstract: Federated continual learning (FCL) evaluates how distributed clients learn from changing data streams while retaining previously learned knowledge. Existing evaluations are difficult to compare because they often change datasets, task splits, client data splits, task orders, backbones, memory assumptions, and reporting rules simultaneously. We introduce \\textbf{HERO}, a heterogeneity-aware benchmark library for FCL. HERO builds benchmark streams by separating three choices that are often coupled, namely the task split, the client data split, and the client task sequence. In HERO-Core, the main comparable benchmark, $\\alpha$ controls client data skew and $\\rho$ controls task-order mismatch. We evaluate representative FCL methods on CIFAR-100 and TinyImageNet using final average accuracy, average forgetting, and bottom-10\\% client accuracy. We also include a graph-based Domain-IL portability case study on OGB-MolPCBA, where scaffold-doma","title":"HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning","url":"https://arxiv.org/abs/2607.08784","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.08784v1 Announce Type: cross \nAbstract: Federated continual learning (FCL) evaluates how distributed clients learn from changing data streams while retaining previously learned knowledge. Existing evaluations are difficult to compare because they often change datasets, task splits, client data splits, task orders, backbones, memory assumptions, and reporting rules simultaneously. We introduce \\textbf{HERO}, a heterogeneity-aware benchmark library for FCL. HERO builds benchmark streams by separating three choices that are often coupled, namely the task split, the client data split, and the client task sequence. In HERO-Core, the main comparable benchmark, $\\alpha$ controls client data skew and $\\rho$ controls task-order mismatch. We evaluate representative FCL methods on CIFAR-100 and TinyImageNet using final average accuracy, average forgetting, and bottom-10\\% client accuracy. We also include a graph-based Domain-IL portability case study on OGB-MolPCBA, where scaffold-doma","title":"HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-13T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.08784"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:efdc8a0d49c73f5da545905800126f856e4a81de7810892e17e0aa5531b7d82e2a7e5d0a3413f7238b4043dab53bfbed1e278943679c090fc2e0a21df20c400b","signer":"crovia.substrate","subject":{"observed_at":"2026-07-13T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.08784"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"2b970d74b44696e7b3fde6d06e15447b5eeabbad31b91722f1e325007c995859","leaf_index":309606,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"f710f787489f219cd7f1af6bd86ecdbbd0f0a0164ec1dd279b51d2dfb9f5a228","side":"right"},{"sibling":"4d2c2edfa983f108fc6ff248bbf5fffcc7749658275384b018cbdf19c650ff91","side":"left"},{"sibling":"e01880f95efceaedbdf71a78635ad0fc3296a492380daaad994a308df94506ee","side":"left"},{"sibling":"629a9754fc35981e17999fd35c5a195a08b341b0e26d389cf79ffa111c1907ea","side":"right"},{"sibling":"7383feb1dbc4d6c131b226bf8db02f81bc3eb73578e8416632d052d441663ec8","side":"right"},{"sibling":"49bd47e1f154959e78cc3d9f153ce1e24052f26978557b543fd908eb4b0989dc","side":"left"},{"sibling":"2b24156380d32b87505f9ff8abbd321b7fb6de2890cac94ceb9223f26203bff0","side":"left"},{"sibling":"1ffbbb6083898ec6beabcbd39595cc5a65c28e8ba2a8441a35ec731530072d34","side":"right"},{"sibling":"6cbb0c4695e74fa8ec17dfde89fa56c1958a1d4dffbbcbe3556da4a69c699ebc","side":"left"},{"sibling":"c4bde3283be97905033d39c1097ac73b82f180de8830384fe6f9f1933f7fa4b9","side":"right"},{"sibling":"3b5f968ebea87e7be458ef7e63c6637988d27ba6d170e1f3794d385cd76ca23f","side":"right"},{"sibling":"5ed534e945b31085c140b50460415e7960b76a4b6266da67d272b853dc94b352","side":"left"},{"sibling":"91010b271bc8eb5253b3549292ef3146e1d85bc9bac7ca36e0862f1204f84e8d","side":"left"},{"sibling":"772fbc112e94d8e574379343387c65503d3cf8fb16ff89090174eccced871a41","side":"left"},{"sibling":"5d50450cae1a230f682b390c8e28ae822ec6c0c04a9bc79b0d27af97306ccccd","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"e9ac4b1e71d3f572751b7984e9ca00893d71628137b4634e82df02cf3db9ab68","side":"right"},{"sibling":"99ff86058e045249bf936a629308be31e4cc71328f0282c4a924f4e6718be5f0","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":309862,"merkle_root":"f18a76abb66e7cb448986b6541091416ed4ebdde8124f5208a7c7c94bb4165d1","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260713T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-13T05:38:23Z","sig_algorithm":"ed25519","signature":"0488e3527b1d559ba55116220f91e2f6c22bb5358a135e8a9b94a65450b50511702044fa993555662ebca09f005b277f5f6ad0d044ec96a5568e9993c09ef007","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_3705f05b1bdbf666002d341c8d3fa507bf8b1f37bf09f15033ca4034165fdb16"}}