{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NCL4LJ37Q4YTRZDM6U6X5N3FLS","short_pith_number":"pith:NCL4LJ37","canonical_record":{"source":{"id":"2605.13807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.str-el","submitted_at":"2026-05-13T17:36:32Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","physics.comp-ph","quant-ph"],"title_canon_sha256":"0107d2e73524fb6f6ced3b3502d55830132cf8e5a68c54875e58a0eba406ceec","abstract_canon_sha256":"0f5bcb9f9a9bb603f5b845a2fe5be8593cde0675ee5199889322669bdeedc76a"},"schema_version":"1.0"},"canonical_sha256":"6897c5a77f873138e46cf53d7eb7655c9e37c9c7171a8c60a8fd4d60cb233475","source":{"kind":"arxiv","id":"2605.13807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13807","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13807v1","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13807","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"NCL4LJ37Q4YT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NCL4LJ37Q4YTRZDM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NCL4LJ37","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NCL4LJ37Q4YTRZDM6U6X5N3FLS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.str-el","submitted_at":"2026-05-13T17:36:32Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","physics.comp-ph","quant-ph"],"title_canon_sha256":"0107d2e73524fb6f6ced3b3502d55830132cf8e5a68c54875e58a0eba406ceec","abstract_canon_sha256":"0f5bcb9f9a9bb603f5b845a2fe5be8593cde0675ee5199889322669bdeedc76a"},"schema_version":"1.0"},"canonical_sha256":"6897c5a77f873138e46cf53d7eb7655c9e37c9c7171a8c60a8fd4d60cb233475","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:15.438632Z","signature_b64":"Yvoa3DJuLgIs/afPoMufF/SbqXVjJ0yE2yzVahPypcVdgNITjLHhqnM6KOMNp1UZn533FOLLcCIIk7xmKXwUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6897c5a77f873138e46cf53d7eb7655c9e37c9c7171a8c60a8fd4d60cb233475","last_reissued_at":"2026-05-18T02:44:15.438080Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:15.438080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13807","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHXTq+s8ngsmDiBX9X/lIlkSOMVXMEJr9RdUwDVgMqQrM8FlSP4AOQpPtuF2yAJmFb9+SNXLArWl8m5TTWMQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T20:26:20.657158Z"},"content_sha256":"a0368fa1177b3a125da47f3e627c771c4edb107c677f84997df8351ef85a9e7d","schema_version":"1.0","event_id":"sha256:a0368fa1177b3a125da47f3e627c771c4edb107c677f84997df8351ef85a9e7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NCL4LJ37Q4YTRZDM6U6X5N3FLS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Recurrent neural networks become parallelizable and reach accurate simulations of 52 by 52 spin lattices in variational Monte Carlo.","cross_cats":["cond-mat.dis-nn","cs.LG","physics.comp-ph","quant-ph"],"primary_cat":"cond-mat.str-el","authors_text":"Ehsan Khatami, Ejaaz Merali, Mohamed Hibat-Allah, Mohammad Kohandel, Richard T. Scalettar","submitted_at":"2026-05-13T17:36:32Z","abstract_excerpt":"Neural-network quantum states have emerged as a powerful variational framework for quantum many-body systems, with recent progress often driven by massively parallel architectures such as transformers. Recurrent neural network quantum states, however, are frequently regarded as intrinsically sequential and therefore less scalable. Here we revisit this view by showing that modern recurrent architectures can support fast, accurate, and computationally accessible neural quantum state simulations. Using autoregressive recurrent wave functions together with recent advances in parallelizable recurre"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"with iterative retraining, our approach reaches two-dimensional spin lattices as large as 52×52 while remaining in agreement with available quantum Monte Carlo data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the autoregressive structure combined with parallel scan recurrence produces a sufficiently expressive variational ansatz whose energy minimum remains close to the true ground state without introducing systematic biases that grow with system size.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PSR-NQS makes recurrent neural quantum states scalable for variational Monte Carlo by using parallel scan recurrence, reaching accurate results on 52x52 two-dimensional lattices.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Recurrent neural networks become parallelizable and reach accurate simulations of 52 by 52 spin lattices in variational Monte Carlo.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2fe5d72970f0470fb89e6d7cb77c69e1380ed62c7fd5347834a5419f1ba60188"},"source":{"id":"2605.13807","kind":"arxiv","version":1},"verdict":{"id":"5046ae5e-e41f-411f-80c3-1755f21ef2e4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T17:36:39.452350Z","strongest_claim":"with iterative retraining, our approach reaches two-dimensional spin lattices as large as 52×52 while remaining in agreement with available quantum Monte Carlo data.","one_line_summary":"PSR-NQS makes recurrent neural quantum states scalable for variational Monte Carlo by using parallel scan recurrence, reaching accurate results on 52x52 two-dimensional lattices.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the autoregressive structure combined with parallel scan recurrence produces a sufficiently expressive variational ansatz whose energy minimum remains close to the true ground state without introducing systematic biases that grow with system size.","pith_extraction_headline":"Recurrent neural networks become parallelizable and reach accurate simulations of 52 by 52 spin lattices in variational Monte Carlo."},"references":{"count":59,"sample":[{"doi":"","year":2017,"title":"F. Becca and S. Sorella,Quantum Monte Carlo Ap- proaches for Correlated Systems(Cambridge University Press, 2017)","work_id":"92781991-4aa8-453a-b4cd-85da4ee3c2c1","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"G. Carleo and M. Troyer, Solving the quantum many- body problem with artificial neural networks, Science 355, 602 (2017)","work_id":"446f62a0-4d1d-49f2-8fd8-dcf9a79da9ff","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"H. Lange, A. Van de Walle, A. Abedinnia, and A. Bohrdt, From architectures to applications: a review of neural quantum states, Quantum Science and Technology9, 040501 (2024)","work_id":"a4d450fd-d9ac-414f-a139-65594d53e101","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"M. Medvidovi´ c and J. R. Moreno, Neural-network quan- tum states for many-body physics, The European Phys- ical Journal Plus139, 631 (2024)","work_id":"65f1f1f6-dc1b-4228-9065-99ee1f118890","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"A. Dawid, J. Arnold, B. Requena, A. Gresch, M. P lodzie´ n, K. Donatella, K. A. Nicoli, P. Stornati, R. Koch, M. B¨ uttner, R. Oku la, G. Mu˜ noz-Gil, R. A. Vargas-Hern´ andez, A. Cervera-Lierta, J. C","work_id":"fdb3eff3-2609-4a7b-85fc-1c0de3d82d9c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":59,"snapshot_sha256":"ddcf97e93951b09a970dd701f34a8c00e32603a5cbcf2e5d61dbd76b5892f545","internal_anchors":12},"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"},"verdict_id":"5046ae5e-e41f-411f-80c3-1755f21ef2e4"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fBBCAsZwm2Ss6ugKHvCmFOT4u1/rff2oXzQnwgZKsXX3CWX7EENcqTg2RCg7WcmDQJSgRu4V0upA8tCrH+DSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T20:26:20.657953Z"},"content_sha256":"0535f474ace6959d68cafc2bac8a1b2513e30be7bc7a1591cbb0341460269dc1","schema_version":"1.0","event_id":"sha256:0535f474ace6959d68cafc2bac8a1b2513e30be7bc7a1591cbb0341460269dc1"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:NCL4LJ37Q4YTRZDM6U6X5N3FLS","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1103/phys-revb.95.195154) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"W.-Y. Liu, S.-J. Dong, Y.-J. Han, G.-C. Guo, and L. He, Gradient optimization of finite projected entan- gled pair states, Physical Review B95, 10.1103/phys- revb.95.195154 (2017)","arxiv_id":"2605.13807","detector":"doi_compliance","evidence":{"ref_index":51,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"W.-Y. Liu, S.-J. Dong, Y.-J. Han, G.-C. Guo, and L. He, Gradient optimization of finite projected entan- gled pair states, Physical Review B95, 10.1103/phys- revb.95.195154 (2017)","reconstructed_doi":"10.1103/phys-revb.95.195154"},"severity":"advisory","ref_index":51,"audited_at":"2026-05-19T06:10:47.385761Z","event_type":"pith.integrity.v1","detected_doi":"10.1103/phys-revb.95.195154","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"549798f8af2465ce1e1813912d31228a00054feb9509559f15f4d8ccda136ed6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":98,"payload_sha256":"cd3a0bcbed78a1a5d159b66f69a90ca8cdc394aa2db68d3b1cc00587a2429ac1","signature_b64":"BlaWdW2TLWfaFqUQPN7iFsnUO/HZqy2EOX4CNrb/VnWAHxJOoITlpq3VuYzcPDDdOI4bOT3hayZmGJ1PuCotAg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T06:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7BwygzfgE2+3qbaEc+SvB4+iofzhGY8A7tiicv+uTajGgABMVC9ew7/r+CbuFaRdeCJJDYwq9mlV5+vvDWxiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T20:26:20.659256Z"},"content_sha256":"2c11d835d8fd9a0ddea555c0359dd2f8155f65b9278cad6a149e0eb132b32e7b","schema_version":"1.0","event_id":"sha256:2c11d835d8fd9a0ddea555c0359dd2f8155f65b9278cad6a149e0eb132b32e7b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:NCL4LJ37Q4YTRZDM6U6X5N3FLS","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1103/physrevre-search.2.023358) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"M. Hibat-Allah, M. Ganahl, L. E. Hayward, R. G. Melko, and J. Carrasquilla, Recurrent neural network wave func- tions, Physical Review Research2, 10.1103/physrevre- search.2.023358 (2020)","arxiv_id":"2605.13807","detector":"doi_compliance","evidence":{"ref_index":8,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"M. Hibat-Allah, M. Ganahl, L. E. Hayward, R. G. Melko, and J. Carrasquilla, Recurrent neural network wave func- tions, Physical Review Research2, 10.1103/physrevre- search.2.023358 (2020)","reconstructed_doi":"10.1103/physrevre-search.2.023358"},"severity":"advisory","ref_index":8,"audited_at":"2026-05-19T06:10:47.385761Z","event_type":"pith.integrity.v1","detected_doi":"10.1103/physrevre-search.2.023358","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"fdd216c36dbf4c2cfdf91a3b6fdb5f64584d584152fcbeb59c5e1d1cc69c3dc9","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":97,"payload_sha256":"301ef49c74f28a8cc58e5d11d568d6c605ec6f3479b11d7f14df7053787b4387","signature_b64":"c0ecIf19yFFYBYqiSmnpOJvNZakIytOvRT34uMD/KorI7BVTnRjGPwFm4nV63ZE0V6/29glzK/wktG0VgDOqBA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T06:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aYPhJiAw/gbmhSZTfIMFjAb9EGcFjbdlGWGhjZ6UfhgbtqLYTaGPeM90C6EJ2DM3XpDOSaZdVfSMVP7qNtFRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T20:26:20.659789Z"},"content_sha256":"db2e7a5da23ad5719a67f2ba53465cce02a5a2567dcf553d4e05f60b5720fbcd","schema_version":"1.0","event_id":"sha256:db2e7a5da23ad5719a67f2ba53465cce02a5a2567dcf553d4e05f60b5720fbcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCL4LJ37Q4YTRZDM6U6X5N3FLS/bundle.json","state_url":"https://pith.science/pith/NCL4LJ37Q4YTRZDM6U6X5N3FLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCL4LJ37Q4YTRZDM6U6X5N3FLS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T20:26:20Z","links":{"resolver":"https://pith.science/pith/NCL4LJ37Q4YTRZDM6U6X5N3FLS","bundle":"https://pith.science/pith/NCL4LJ37Q4YTRZDM6U6X5N3FLS/bundle.json","state":"https://pith.science/pith/NCL4LJ37Q4YTRZDM6U6X5N3FLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCL4LJ37Q4YTRZDM6U6X5N3FLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NCL4LJ37Q4YTRZDM6U6X5N3FLS","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0f5bcb9f9a9bb603f5b845a2fe5be8593cde0675ee5199889322669bdeedc76a","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","physics.comp-ph","quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.str-el","submitted_at":"2026-05-13T17:36:32Z","title_canon_sha256":"0107d2e73524fb6f6ced3b3502d55830132cf8e5a68c54875e58a0eba406ceec"},"schema_version":"1.0","source":{"id":"2605.13807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13807","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13807v1","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13807","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"NCL4LJ37Q4YT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NCL4LJ37Q4YTRZDM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NCL4LJ37","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:0535f474ace6959d68cafc2bac8a1b2513e30be7bc7a1591cbb0341460269dc1","target":"graph","created_at":"2026-05-18T02:44:15Z","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":"with iterative retraining, our approach reaches two-dimensional spin lattices as large as 52×52 while remaining in agreement with available quantum Monte Carlo data."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the autoregressive structure combined with parallel scan recurrence produces a sufficiently expressive variational ansatz whose energy minimum remains close to the true ground state without introducing systematic biases that grow with system size."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PSR-NQS makes recurrent neural quantum states scalable for variational Monte Carlo by using parallel scan recurrence, reaching accurate results on 52x52 two-dimensional lattices."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Recurrent neural networks become parallelizable and reach accurate simulations of 52 by 52 spin lattices in variational Monte Carlo."}],"snapshot_sha256":"2fe5d72970f0470fb89e6d7cb77c69e1380ed62c7fd5347834a5419f1ba60188"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Neural-network quantum states have emerged as a powerful variational framework for quantum many-body systems, with recent progress often driven by massively parallel architectures such as transformers. Recurrent neural network quantum states, however, are frequently regarded as intrinsically sequential and therefore less scalable. Here we revisit this view by showing that modern recurrent architectures can support fast, accurate, and computationally accessible neural quantum state simulations. Using autoregressive recurrent wave functions together with recent advances in parallelizable recurre","authors_text":"Ehsan Khatami, Ejaaz Merali, Mohamed Hibat-Allah, Mohammad Kohandel, Richard T. Scalettar","cross_cats":["cond-mat.dis-nn","cs.LG","physics.comp-ph","quant-ph"],"headline":"Recurrent neural networks become parallelizable and reach accurate simulations of 52 by 52 spin lattices in variational Monte Carlo.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.str-el","submitted_at":"2026-05-13T17:36:32Z","title":"Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo"},"references":{"count":59,"internal_anchors":12,"resolved_work":59,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"F. Becca and S. Sorella,Quantum Monte Carlo Ap- proaches for Correlated Systems(Cambridge University Press, 2017)","work_id":"92781991-4aa8-453a-b4cd-85da4ee3c2c1","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"G. Carleo and M. Troyer, Solving the quantum many- body problem with artificial neural networks, Science 355, 602 (2017)","work_id":"446f62a0-4d1d-49f2-8fd8-dcf9a79da9ff","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"H. Lange, A. Van de Walle, A. Abedinnia, and A. Bohrdt, From architectures to applications: a review of neural quantum states, Quantum Science and Technology9, 040501 (2024)","work_id":"a4d450fd-d9ac-414f-a139-65594d53e101","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"M. Medvidovi´ c and J. R. Moreno, Neural-network quan- tum states for many-body physics, The European Phys- ical Journal Plus139, 631 (2024)","work_id":"65f1f1f6-dc1b-4228-9065-99ee1f118890","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"A. Dawid, J. Arnold, B. Requena, A. Gresch, M. P lodzie´ n, K. Donatella, K. A. Nicoli, P. Stornati, R. Koch, M. B¨ uttner, R. Oku la, G. Mu˜ noz-Gil, R. A. Vargas-Hern´ andez, A. Cervera-Lierta, J. C","work_id":"fdb3eff3-2609-4a7b-85fc-1c0de3d82d9c","year":2025}],"snapshot_sha256":"ddcf97e93951b09a970dd701f34a8c00e32603a5cbcf2e5d61dbd76b5892f545"},"source":{"id":"2605.13807","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T17:36:39.452350Z","id":"5046ae5e-e41f-411f-80c3-1755f21ef2e4","model_set":{"reader":"grok-4.3"},"one_line_summary":"PSR-NQS makes recurrent neural quantum states scalable for variational Monte Carlo by using parallel scan recurrence, reaching accurate results on 52x52 two-dimensional lattices.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Recurrent neural networks become parallelizable and reach accurate simulations of 52 by 52 spin lattices in variational Monte Carlo.","strongest_claim":"with iterative retraining, our approach reaches two-dimensional spin lattices as large as 52×52 while remaining in agreement with available quantum Monte Carlo data.","weakest_assumption":"That the autoregressive structure combined with parallel scan recurrence produces a sufficiently expressive variational ansatz whose energy minimum remains close to the true ground state without introducing systematic biases that grow with system size."}},"verdict_id":"5046ae5e-e41f-411f-80c3-1755f21ef2e4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a0368fa1177b3a125da47f3e627c771c4edb107c677f84997df8351ef85a9e7d","target":"record","created_at":"2026-05-18T02:44:15Z","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":"0f5bcb9f9a9bb603f5b845a2fe5be8593cde0675ee5199889322669bdeedc76a","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","physics.comp-ph","quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.str-el","submitted_at":"2026-05-13T17:36:32Z","title_canon_sha256":"0107d2e73524fb6f6ced3b3502d55830132cf8e5a68c54875e58a0eba406ceec"},"schema_version":"1.0","source":{"id":"2605.13807","kind":"arxiv","version":1}},"canonical_sha256":"6897c5a77f873138e46cf53d7eb7655c9e37c9c7171a8c60a8fd4d60cb233475","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6897c5a77f873138e46cf53d7eb7655c9e37c9c7171a8c60a8fd4d60cb233475","first_computed_at":"2026-05-18T02:44:15.438080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:15.438080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yvoa3DJuLgIs/afPoMufF/SbqXVjJ0yE2yzVahPypcVdgNITjLHhqnM6KOMNp1UZn533FOLLcCIIk7xmKXwUBw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:15.438632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13807","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:2c11d835d8fd9a0ddea555c0359dd2f8155f65b9278cad6a149e0eb132b32e7b","sha256:db2e7a5da23ad5719a67f2ba53465cce02a5a2567dcf553d4e05f60b5720fbcd"]}],"invalid_events":[],"applied_event_ids":["sha256:a0368fa1177b3a125da47f3e627c771c4edb107c677f84997df8351ef85a9e7d","sha256:0535f474ace6959d68cafc2bac8a1b2513e30be7bc7a1591cbb0341460269dc1"],"state_sha256":"d93433d9d6324771fa771cf801870ac80f0a2a335e562298f64b28ad8cbe170f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"njMnowdDmzJdXvDR41GEnRJCPdnolEfmhyqmLFJiJQATLXFmb5Nfvcp+CxGP5k8hGARDG9k6e3lCbKsReF8VCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T20:26:20.663959Z","bundle_sha256":"63b57bedc8041c08bde7f4ac35a3cf091ece61441a17d7832bae310c4b979f36"}}