{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AS5UUDEFH525664JTKSFJT7IMM","short_pith_number":"pith:AS5UUDEF","schema_version":"1.0","canonical_sha256":"04bb4a0c853f75df7b899aa454cfe86308454f7b474dbdd88903f76e623e5804","source":{"kind":"arxiv","id":"2605.17361","version":1},"attestation_state":"computed","paper":{"title":"\\textsc{MasFACT}: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Di Zhang, Fengbo Zhang, Jialu Wang, Jun Han, Ruijie Wang, Xuefei Wang, Yihan Hu, Yikun Ban, Yutong Ye","submitted_at":"2026-05-17T09:58:58Z","abstract_excerpt":"Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance critically depends on the underlying inter-agent communication topology. However, existing topology generation methods mainly optimize for isolated tasks, while real-world deployments involve streams of evolving tasks, requiring previously effective collaboration patterns to be retained and reused rather than rediscovered or overwritten. We identify a previously underexplored failure mode, \\emph{topology forgetting}, in which adapting to new tasks"},"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":"2605.17361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T09:58:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70b9ef08f65858ffe257862ade56716ca13b5e9500cb7885b0cc35a99737c6cc","abstract_canon_sha256":"55e13c3c1d02aa1f2a07fe6e8f8809bfabda77e728f2440dcf84c3ffc190ee31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:54.339091Z","signature_b64":"m9QkvPyN4mLK6N5QHDqzZXV3hdncquuNOJggX64ycbZwmFFK2GcDOZPt95yLddyASJtNKqJTHMvbL6F3cPMSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04bb4a0c853f75df7b899aa454cfe86308454f7b474dbdd88903f76e623e5804","last_reissued_at":"2026-05-20T00:03:54.338339Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:54.338339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\\textsc{MasFACT}: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Di Zhang, Fengbo Zhang, Jialu Wang, Jun Han, Ruijie Wang, Xuefei Wang, Yihan Hu, Yikun Ban, Yutong Ye","submitted_at":"2026-05-17T09:58:58Z","abstract_excerpt":"Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance critically depends on the underlying inter-agent communication topology. However, existing topology generation methods mainly optimize for isolated tasks, while real-world deployments involve streams of evolving tasks, requiring previously effective collaboration patterns to be retained and reused rather than rediscovered or overwritten. We identify a previously underexplored failure mode, \\emph{topology forgetting}, in which adapting to new tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17361","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/2605.17361/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.785922Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.720332Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f7371d5c6faf759773126a753c1e6ae7607404ad0af88254d59a48778ab52224"},"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":"2605.17361","created_at":"2026-05-20T00:03:54.338453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17361v1","created_at":"2026-05-20T00:03:54.338453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17361","created_at":"2026-05-20T00:03:54.338453+00:00"},{"alias_kind":"pith_short_12","alias_value":"AS5UUDEFH525","created_at":"2026-05-20T00:03:54.338453+00:00"},{"alias_kind":"pith_short_16","alias_value":"AS5UUDEFH525664J","created_at":"2026-05-20T00:03:54.338453+00:00"},{"alias_kind":"pith_short_8","alias_value":"AS5UUDEF","created_at":"2026-05-20T00:03:54.338453+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/AS5UUDEFH525664JTKSFJT7IMM","json":"https://pith.science/pith/AS5UUDEFH525664JTKSFJT7IMM.json","graph_json":"https://pith.science/api/pith-number/AS5UUDEFH525664JTKSFJT7IMM/graph.json","events_json":"https://pith.science/api/pith-number/AS5UUDEFH525664JTKSFJT7IMM/events.json","paper":"https://pith.science/paper/AS5UUDEF"},"agent_actions":{"view_html":"https://pith.science/pith/AS5UUDEFH525664JTKSFJT7IMM","download_json":"https://pith.science/pith/AS5UUDEFH525664JTKSFJT7IMM.json","view_paper":"https://pith.science/paper/AS5UUDEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17361&json=true","fetch_graph":"https://pith.science/api/pith-number/AS5UUDEFH525664JTKSFJT7IMM/graph.json","fetch_events":"https://pith.science/api/pith-number/AS5UUDEFH525664JTKSFJT7IMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AS5UUDEFH525664JTKSFJT7IMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AS5UUDEFH525664JTKSFJT7IMM/action/storage_attestation","attest_author":"https://pith.science/pith/AS5UUDEFH525664JTKSFJT7IMM/action/author_attestation","sign_citation":"https://pith.science/pith/AS5UUDEFH525664JTKSFJT7IMM/action/citation_signature","submit_replication":"https://pith.science/pith/AS5UUDEFH525664JTKSFJT7IMM/action/replication_record"}},"created_at":"2026-05-20T00:03:54.338453+00:00","updated_at":"2026-05-20T00:03:54.338453+00:00"}