{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NJ2ZSZMRRLBCE25QHNMAZHYEED","short_pith_number":"pith:NJ2ZSZMR","canonical_record":{"source":{"id":"2604.12198","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-04-14T02:06:59Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"427a8a4592466108266324ba84afa1ef2427f66ef2d092c2177e244635259e27","abstract_canon_sha256":"ec8f0d567f493b6e47534b961ceef9079dd402e208cd955b70fb6971f69c9caa"},"schema_version":"1.0"},"canonical_sha256":"6a759965918ac2226bb03b580c9f0420ddd3efe857b99074b81a0d4cd2e667fa","source":{"kind":"arxiv","id":"2604.12198","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.12198","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"arxiv_version","alias_value":"2604.12198v2","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12198","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"pith_short_12","alias_value":"NJ2ZSZMRRLBC","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"pith_short_16","alias_value":"NJ2ZSZMRRLBCE25Q","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"pith_short_8","alias_value":"NJ2ZSZMR","created_at":"2026-07-03T01:17:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NJ2ZSZMRRLBCE25QHNMAZHYEED","target":"record","payload":{"canonical_record":{"source":{"id":"2604.12198","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-04-14T02:06:59Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"427a8a4592466108266324ba84afa1ef2427f66ef2d092c2177e244635259e27","abstract_canon_sha256":"ec8f0d567f493b6e47534b961ceef9079dd402e208cd955b70fb6971f69c9caa"},"schema_version":"1.0"},"canonical_sha256":"6a759965918ac2226bb03b580c9f0420ddd3efe857b99074b81a0d4cd2e667fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:55.158334Z","signature_b64":"sNNJsSnbAGYkn7a0A4YtIjqZaO0EkMzsHIuBx9KkpHPbCSAT77vbnFfJVSsc8VlklZ9NWrAa5Vh8cYQb7yNYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a759965918ac2226bb03b580c9f0420ddd3efe857b99074b81a0d4cd2e667fa","last_reissued_at":"2026-07-03T01:17:55.157783Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:55.157783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.12198","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-03T01:17:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JdPZkjHu2jyC4vIMkXpJlOuADIT//18r8boASQ4ZB8DQavD7CXSQP3prRs11rsVfsqb2rqQo2z56u1y93G1xAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:38:16.505999Z"},"content_sha256":"ed318c6649698842f2b7107eb5ca1229be7a135d2d4df6a5b903f1e0ce749491","schema_version":"1.0","event_id":"sha256:ed318c6649698842f2b7107eb5ca1229be7a135d2d4df6a5b903f1e0ce749491"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NJ2ZSZMRRLBCE25QHNMAZHYEED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounded autonomous scrutiny at scale: emergent critique from reproduction of published computational physics papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An LLM agent can autonomously read published computational physics papers, reproduce their calculations, raise substantive concerns on 42% of them, and generate a publishable Comment that revises a Nature paper's headline conclusion.","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"primary_cat":"physics.comp-ph","authors_text":"Haonan Huang","submitted_at":"2026-04-14T02:06:59Z","abstract_excerpt":"Autonomous LLM agents now produce complete research artifacts in machine-learning sandboxes, but real computational physics is harder: experiments are first-principles calculations against re-runnable physical ground truth, and meaningful new work almost always builds on a key existing paper. We ask whether such an agent can perform grounded scrutiny of published computational physics - reading a paper, reproducing it from scratch, and surfacing methodological concerns from execution. We deploy a single Claude Opus 4.6 configuration at two complementary scopes. At scale, across 111 open-access"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"an agent autonomously runs the read-plan-compute-compare loop and, without being asked to critique, raises substantive concerns on ~42% of papers - 97.7% of which require execution to surface. In depth, for one Nature Communications paper on multiscale simulation of a 2D-material MOSFET, the agent runs new calculations missing from the original and produces, unsupervised, a publishable Comment -- composed, figured, typeset, and PDF-iterated -- that revises the paper's headline conclusion.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the agent's identified 'substantive concerns' are valid and that the generated Comment is accurate and genuinely publishable without independent human verification or external peer review.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An LLM agent autonomously runs read-plan-compute-compare loops on 111 computational physics papers, raising substantive concerns in 42% of them (97.7% only after execution), and generates a full publishable Comment revising the headline conclusion of a Nature Communications paper on 2D-material MOFs","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An LLM agent can autonomously read published computational physics papers, reproduce their calculations, raise substantive concerns on 42% of them, and generate a publishable Comment that revises a Nature paper's headline conclusion.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"eeaa3fb587779d7d9d906339c3349185d25a56ec7bea56485446d9c4d2990376"},"source":{"id":"2604.12198","kind":"arxiv","version":2},"verdict":{"id":"bf6861f0-e625-4ff3-aa13-5753154af649","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T14:25:23.384184Z","strongest_claim":"an agent autonomously runs the read-plan-compute-compare loop and, without being asked to critique, raises substantive concerns on ~42% of papers - 97.7% of which require execution to surface. In depth, for one Nature Communications paper on multiscale simulation of a 2D-material MOSFET, the agent runs new calculations missing from the original and produces, unsupervised, a publishable Comment -- composed, figured, typeset, and PDF-iterated -- that revises the paper's headline conclusion.","one_line_summary":"An LLM agent autonomously runs read-plan-compute-compare loops on 111 computational physics papers, raising substantive concerns in 42% of them (97.7% only after execution), and generates a full publishable Comment revising the headline conclusion of a Nature Communications paper on 2D-material MOFs","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the agent's identified 'substantive concerns' are valid and that the generated Comment is accurate and genuinely publishable without independent human verification or external peer review.","pith_extraction_headline":"An LLM agent can autonomously read published computational physics papers, reproduce their calculations, raise substantive concerns on 42% of them, and generate a publishable Comment that revises a Nature paper's headline conclusion."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.12198/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"},"verdict_id":"bf6861f0-e625-4ff3-aa13-5753154af649"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-03T01:17:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBQTi8ATLBm22+Yd8sZ/MZR2f1atoiCMTEVV8cCZ4h86sQuqY5CwSKF2WgCvtu8SZdh6NnyYx08+S7PhrksEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:38:16.506482Z"},"content_sha256":"6d979219f47191a0a9a2d665eaa5ec82dd980310da686e6b64e9ab8d9738f648","schema_version":"1.0","event_id":"sha256:6d979219f47191a0a9a2d665eaa5ec82dd980310da686e6b64e9ab8d9738f648"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJ2ZSZMRRLBCE25QHNMAZHYEED/bundle.json","state_url":"https://pith.science/pith/NJ2ZSZMRRLBCE25QHNMAZHYEED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJ2ZSZMRRLBCE25QHNMAZHYEED/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":"2026-07-07T11:38:16Z","links":{"resolver":"https://pith.science/pith/NJ2ZSZMRRLBCE25QHNMAZHYEED","bundle":"https://pith.science/pith/NJ2ZSZMRRLBCE25QHNMAZHYEED/bundle.json","state":"https://pith.science/pith/NJ2ZSZMRRLBCE25QHNMAZHYEED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJ2ZSZMRRLBCE25QHNMAZHYEED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NJ2ZSZMRRLBCE25QHNMAZHYEED","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":"ec8f0d567f493b6e47534b961ceef9079dd402e208cd955b70fb6971f69c9caa","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-04-14T02:06:59Z","title_canon_sha256":"427a8a4592466108266324ba84afa1ef2427f66ef2d092c2177e244635259e27"},"schema_version":"1.0","source":{"id":"2604.12198","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.12198","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"arxiv_version","alias_value":"2604.12198v2","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12198","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"pith_short_12","alias_value":"NJ2ZSZMRRLBC","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"pith_short_16","alias_value":"NJ2ZSZMRRLBCE25Q","created_at":"2026-07-03T01:17:55Z"},{"alias_kind":"pith_short_8","alias_value":"NJ2ZSZMR","created_at":"2026-07-03T01:17:55Z"}],"graph_snapshots":[{"event_id":"sha256:6d979219f47191a0a9a2d665eaa5ec82dd980310da686e6b64e9ab8d9738f648","target":"graph","created_at":"2026-07-03T01:17:55Z","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":"an agent autonomously runs the read-plan-compute-compare loop and, without being asked to critique, raises substantive concerns on ~42% of papers - 97.7% of which require execution to surface. In depth, for one Nature Communications paper on multiscale simulation of a 2D-material MOSFET, the agent runs new calculations missing from the original and produces, unsupervised, a publishable Comment -- composed, figured, typeset, and PDF-iterated -- that revises the paper's headline conclusion."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the agent's identified 'substantive concerns' are valid and that the generated Comment is accurate and genuinely publishable without independent human verification or external peer review."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"An LLM agent autonomously runs read-plan-compute-compare loops on 111 computational physics papers, raising substantive concerns in 42% of them (97.7% only after execution), and generates a full publishable Comment revising the headline conclusion of a Nature Communications paper on 2D-material MOFs"},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An LLM agent can autonomously read published computational physics papers, reproduce their calculations, raise substantive concerns on 42% of them, and generate a publishable Comment that revises a Nature paper's headline conclusion."}],"snapshot_sha256":"eeaa3fb587779d7d9d906339c3349185d25a56ec7bea56485446d9c4d2990376"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.12198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous LLM agents now produce complete research artifacts in machine-learning sandboxes, but real computational physics is harder: experiments are first-principles calculations against re-runnable physical ground truth, and meaningful new work almost always builds on a key existing paper. We ask whether such an agent can perform grounded scrutiny of published computational physics - reading a paper, reproducing it from scratch, and surfacing methodological concerns from execution. We deploy a single Claude Opus 4.6 configuration at two complementary scopes. At scale, across 111 open-access","authors_text":"Haonan Huang","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"headline":"An LLM agent can autonomously read published computational physics papers, reproduce their calculations, raise substantive concerns on 42% of them, and generate a publishable Comment that revises a Nature paper's headline conclusion.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-04-14T02:06:59Z","title":"Grounded autonomous scrutiny at scale: emergent critique from reproduction of published computational physics papers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.12198","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T14:25:23.384184Z","id":"bf6861f0-e625-4ff3-aa13-5753154af649","model_set":{"reader":"grok-4.3"},"one_line_summary":"An LLM agent autonomously runs read-plan-compute-compare loops on 111 computational physics papers, raising substantive concerns in 42% of them (97.7% only after execution), and generates a full publishable Comment revising the headline conclusion of a Nature Communications paper on 2D-material MOFs","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"An LLM agent can autonomously read published computational physics papers, reproduce their calculations, raise substantive concerns on 42% of them, and generate a publishable Comment that revises a Nature paper's headline conclusion.","strongest_claim":"an agent autonomously runs the read-plan-compute-compare loop and, without being asked to critique, raises substantive concerns on ~42% of papers - 97.7% of which require execution to surface. In depth, for one Nature Communications paper on multiscale simulation of a 2D-material MOSFET, the agent runs new calculations missing from the original and produces, unsupervised, a publishable Comment -- composed, figured, typeset, and PDF-iterated -- that revises the paper's headline conclusion.","weakest_assumption":"That the agent's identified 'substantive concerns' are valid and that the generated Comment is accurate and genuinely publishable without independent human verification or external peer review."}},"verdict_id":"bf6861f0-e625-4ff3-aa13-5753154af649"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ed318c6649698842f2b7107eb5ca1229be7a135d2d4df6a5b903f1e0ce749491","target":"record","created_at":"2026-07-03T01:17:55Z","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":"ec8f0d567f493b6e47534b961ceef9079dd402e208cd955b70fb6971f69c9caa","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-04-14T02:06:59Z","title_canon_sha256":"427a8a4592466108266324ba84afa1ef2427f66ef2d092c2177e244635259e27"},"schema_version":"1.0","source":{"id":"2604.12198","kind":"arxiv","version":2}},"canonical_sha256":"6a759965918ac2226bb03b580c9f0420ddd3efe857b99074b81a0d4cd2e667fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a759965918ac2226bb03b580c9f0420ddd3efe857b99074b81a0d4cd2e667fa","first_computed_at":"2026-07-03T01:17:55.157783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:55.157783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sNNJsSnbAGYkn7a0A4YtIjqZaO0EkMzsHIuBx9KkpHPbCSAT77vbnFfJVSsc8VlklZ9NWrAa5Vh8cYQb7yNYAQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:55.158334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.12198","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed318c6649698842f2b7107eb5ca1229be7a135d2d4df6a5b903f1e0ce749491","sha256:6d979219f47191a0a9a2d665eaa5ec82dd980310da686e6b64e9ab8d9738f648"],"state_sha256":"af473c6ead8efbbb2773f47b0d0056e1fce460b646a5fd8a36d8a6c5b81d20fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aKYA9/TUizqtShZJbh6neaDBiBRQGq7FVdfkfTPKn3Pelf7qo/YPeTgkYmfIfZF8PPz20qiXHxzkZwvrmgdhBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:38:16.508624Z","bundle_sha256":"e4a6ecad1f09e4ea6acfb3ad8cba587f86f7b7e2f732cc2f4a4ba979104fc310"}}