{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BEB4DDRJN7AFW7KX65CHFB2NRE","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":"52c1e8a910aefe1279267a1cc1ad20129a6ae1e88b1d2e6a810592c42a17e735","cross_cats_sorted":["cs.CC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2026-05-14T16:29:05Z","title_canon_sha256":"184bbdd36d52031bdfcaebc1d21b401e029f3d55951a9c52bb22ca8503e30074"},"schema_version":"1.0","source":{"id":"2605.15033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15033","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15033v1","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15033","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"BEB4DDRJN7AF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BEB4DDRJN7AFW7KX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BEB4DDRJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:a9d80d621bd2f5579486f0057161eae9c83cf9799665dc39906db7631d6f265b","target":"graph","created_at":"2026-05-17T23:38:54Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"if the opinion dynamics follow a threshold rule in which a fixed number of influencers prevent opinion change (e.g., unanimity and quasi-unanimity), we provide an efficient PAC learning algorithm provided that the number of influencers per agent is bounded. ... if agents' opinions follow the majority of their influencers, then there is no efficient PAC learning algorithm."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The opinion updates exactly follow a deterministic threshold rule with a fixed number of influencers per agent (or exactly majority), and the samples are drawn from the synchronous update process without noise or hidden variables."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PAC learning of networks from threshold opinion dynamics is efficient when influencers per agent are bounded but computationally hard for majority rules, with a heuristic succeeding in over 98% of simulations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Networks with unanimity-style opinion updates can be learned efficiently from samples via PAC algorithms when each agent has a bounded number of influencers, but majority updates make efficient learning impossible under standard complexity."}],"snapshot_sha256":"cef84fb33ddeab206b9f173286b3d0e4f0e719293b686d604e000b78adc6a638"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Agents in social networks with threshold-based dynamics change opinions when influenced by sufficiently many peers. Existing literature typically assumes that the network structure and dynamics are fully known, which is often unrealistic. In this work, we ask how to learn a network structure from samples of the agents' synchronous opinion updates. Firstly, if the opinion dynamics follow a threshold rule in which a fixed number of influencers prevent opinion change (e.g., unanimity and quasi-unanimity), we provide an efficient PAC learning algorithm provided that the number of influencers per a","authors_text":"Dmitry Chistikov, Luisa Estrada, Mike Paterson, Paolo Turrini","cross_cats":["cs.CC"],"headline":"Networks with unanimity-style opinion updates can be learned efficiently from samples via PAC algorithms when each agent has a bounded number of influencers, but majority updates make efficient learning impossible under standard complexity.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2026-05-14T16:29:05Z","title":"On the Limits of PAC Learning of Networks from Opinion Dynamics"},"references":{"count":40,"internal_anchors":1,"resolved_work":40,"sample":[{"cited_arxiv_id":"","doi":"10.1006/jeth","is_internal_anchor":false,"ref_index":1,"title":"Jour- nal of Economic Theory106(2), 265–295 (2002) https://doi.org/10.1006/jeth","work_id":"d8afbf67-97bb-4dfd-8c7c-796aaca5e331","year":2002},{"cited_arxiv_id":"1902.03779","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Election Manipulation on Social Networks with Messages on Multiple Candidates","work_id":"3771e195-d000-448e-9ec2-063873635061","year":1902},{"cited_arxiv_id":"","doi":"10.1145/1281192.1281239","is_internal_anchor":false,"ref_index":4,"title":"In: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery And Data Mining","work_id":"430843b3-e0a9-4f9e-9525-1b4a1bb03a0c","year":2007},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"In: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems","work_id":"eb48cefc-892d-4b17-8cef-2141e8b198b4","year":2023},{"cited_arxiv_id":"","doi":"10.1016/j.tpb.2013.06.006","is_internal_anchor":false,"ref_index":6,"title":"Theoretical Population Biology88, 68–77 (2013) https://doi.org/10.1016/j.tpb.2013.06.006","work_id":"4e50596c-0ede-4c6a-86f7-35efad4e0974","year":2013}],"snapshot_sha256":"753056ce957efd167df31954d163bac7eadffb8484e8f7b5bbcef2b92ac72d80"},"source":{"id":"2605.15033","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:05:54.382190Z","id":"ef9a61bb-0c5a-4285-a701-1e1131eecbc2","model_set":{"reader":"grok-4.3"},"one_line_summary":"PAC learning of networks from threshold opinion dynamics is efficient when influencers per agent are bounded but computationally hard for majority rules, with a heuristic succeeding in over 98% of simulations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Networks with unanimity-style opinion updates can be learned efficiently from samples via PAC algorithms when each agent has a bounded number of influencers, but majority updates make efficient learning impossible under standard complexity.","strongest_claim":"if the opinion dynamics follow a threshold rule in which a fixed number of influencers prevent opinion change (e.g., unanimity and quasi-unanimity), we provide an efficient PAC learning algorithm provided that the number of influencers per agent is bounded. ... if agents' opinions follow the majority of their influencers, then there is no efficient PAC learning algorithm.","weakest_assumption":"The opinion updates exactly follow a deterministic threshold rule with a fixed number of influencers per agent (or exactly majority), and the samples are drawn from the synchronous update process without noise or hidden variables."}},"verdict_id":"ef9a61bb-0c5a-4285-a701-1e1131eecbc2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2637db83311a51b53e069674ae549d2b1917d633d1e7231f5054b744ba2612cf","target":"record","created_at":"2026-05-17T23:38:54Z","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":"52c1e8a910aefe1279267a1cc1ad20129a6ae1e88b1d2e6a810592c42a17e735","cross_cats_sorted":["cs.CC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2026-05-14T16:29:05Z","title_canon_sha256":"184bbdd36d52031bdfcaebc1d21b401e029f3d55951a9c52bb22ca8503e30074"},"schema_version":"1.0","source":{"id":"2605.15033","kind":"arxiv","version":1}},"canonical_sha256":"0903c18e296fc05b7d57f74472874d89307f3d845eea9021ce67a40b74c09b75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0903c18e296fc05b7d57f74472874d89307f3d845eea9021ce67a40b74c09b75","first_computed_at":"2026-05-17T23:38:54.562030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:54.562030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tx6KQj0Id4C4Mn5Fe3PrCIia2QE3/HubqmXp/aYoBJh0jUyoZnFqaqOR35mOioZYv5Nba5jY22hN0JdxhA6DAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:54.562689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2637db83311a51b53e069674ae549d2b1917d633d1e7231f5054b744ba2612cf","sha256:a9d80d621bd2f5579486f0057161eae9c83cf9799665dc39906db7631d6f265b"],"state_sha256":"61697bfbdf9b0fa6ab35853c51db54c1642b2552befd7e80bc48057876c08e34"}