{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HTFJUAGSMHAGOSATZVJ5WAH7D3","short_pith_number":"pith:HTFJUAGS","schema_version":"1.0","canonical_sha256":"3cca9a00d261c0674813cd53db00ff1ee7b9cde84f38ad17e049a97568c1a200","source":{"kind":"arxiv","id":"2108.09330","version":3},"attestation_state":"computed","paper":{"title":"Conformal Bootstrap with Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"hep-th","authors_text":"Constantinos Papageorgakis, Gergely K\\'antor, Vasilis Niarchos","submitted_at":"2021-08-20T18:43:59Z","abstract_excerpt":"We introduce the use of reinforcement-learning (RL) techniques to the conformal-bootstrap programme. We demonstrate that suitable soft Actor-Critic RL algorithms can perform efficient, relatively cheap high-dimensional searches in the space of scaling dimensions and OPE-squared coefficients that produce sensible results for tens of CFT data from a single crossing equation. In this paper we test this approach in well-known 2D CFTs, with particular focus on the Ising and tri-critical Ising models and the free compactified boson CFT. We present results of as high as 36-dimensional searches, whose"},"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":"2108.09330","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-th","submitted_at":"2021-08-20T18:43:59Z","cross_cats_sorted":[],"title_canon_sha256":"2f44d5f4dfa1a79b7877dfaefa51e6091dac1c3f921d61f07be4a6f0167327e7","abstract_canon_sha256":"9b2febc584e20681fbec4628f18405baa5235ffff689560546cb05a5aa0cee95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:03.066398Z","signature_b64":"/Kxw6v/j93c+AJWTuhvzSPuOeSrVrDkS8AZVLdw96eEJs+yiABlPuDAMe2BQ/g1QvB3NK2+MU1Tbf1mbOTXSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cca9a00d261c0674813cd53db00ff1ee7b9cde84f38ad17e049a97568c1a200","last_reissued_at":"2026-07-05T03:53:03.065848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:03.065848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conformal Bootstrap with Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"hep-th","authors_text":"Constantinos Papageorgakis, Gergely K\\'antor, Vasilis Niarchos","submitted_at":"2021-08-20T18:43:59Z","abstract_excerpt":"We introduce the use of reinforcement-learning (RL) techniques to the conformal-bootstrap programme. We demonstrate that suitable soft Actor-Critic RL algorithms can perform efficient, relatively cheap high-dimensional searches in the space of scaling dimensions and OPE-squared coefficients that produce sensible results for tens of CFT data from a single crossing equation. In this paper we test this approach in well-known 2D CFTs, with particular focus on the Ising and tri-critical Ising models and the free compactified boson CFT. We present results of as high as 36-dimensional searches, whose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09330","kind":"arxiv","version":3},"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/2108.09330/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":"2108.09330","created_at":"2026-07-05T03:53:03.065909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.09330v3","created_at":"2026-07-05T03:53:03.065909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09330","created_at":"2026-07-05T03:53:03.065909+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTFJUAGSMHAG","created_at":"2026-07-05T03:53:03.065909+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTFJUAGSMHAGOSAT","created_at":"2026-07-05T03:53:03.065909+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTFJUAGS","created_at":"2026-07-05T03:53:03.065909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16119","citing_title":"Boundary anomalous dimensions from BCFT: $\\phi^{3}$ theories with a boundary and higher-derivative generalizations","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10627","citing_title":"Efficient Conformal Block Evaluation with GoBlocks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13183","citing_title":"Neural Networks, Dispersion Relations and the Thermal Bootstrap","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01275","citing_title":"Descending into the Modular Bootstrap","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18686","citing_title":"Neural Spectral Bias and Conformal Correlators I: Introduction and Applications","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3","json":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3.json","graph_json":"https://pith.science/api/pith-number/HTFJUAGSMHAGOSATZVJ5WAH7D3/graph.json","events_json":"https://pith.science/api/pith-number/HTFJUAGSMHAGOSATZVJ5WAH7D3/events.json","paper":"https://pith.science/paper/HTFJUAGS"},"agent_actions":{"view_html":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3","download_json":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3.json","view_paper":"https://pith.science/paper/HTFJUAGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.09330&json=true","fetch_graph":"https://pith.science/api/pith-number/HTFJUAGSMHAGOSATZVJ5WAH7D3/graph.json","fetch_events":"https://pith.science/api/pith-number/HTFJUAGSMHAGOSATZVJ5WAH7D3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3/action/storage_attestation","attest_author":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3/action/author_attestation","sign_citation":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3/action/citation_signature","submit_replication":"https://pith.science/pith/HTFJUAGSMHAGOSATZVJ5WAH7D3/action/replication_record"}},"created_at":"2026-07-05T03:53:03.065909+00:00","updated_at":"2026-07-05T03:53:03.065909+00:00"}