{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PSZKMCJF5WEI7HX3NAPPG4WK3E","short_pith_number":"pith:PSZKMCJF","canonical_record":{"source":{"id":"2506.20729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T18:00:18Z","cross_cats_sorted":["astro-ph.CO","cs.AI","hep-ph","hep-th"],"title_canon_sha256":"475576ede13ae2e271703615b3af73692433fad11a2d8ab1d4625c75a6d5d915","abstract_canon_sha256":"24d65d91da905bf0681d80e492bc2e1a095e2cc83b9d4bfef56583cc8def53b7"},"schema_version":"1.0"},"canonical_sha256":"7cb2a60925ed888f9efb681ef372cad929a3fad2e135af0a490e77cdce8b7847","source":{"kind":"arxiv","id":"2506.20729","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20729","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20729v1","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20729","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"PSZKMCJF5WEI","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"PSZKMCJF5WEI7HX3","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"PSZKMCJF","created_at":"2026-07-05T11:27:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PSZKMCJF5WEI7HX3NAPPG4WK3E","target":"record","payload":{"canonical_record":{"source":{"id":"2506.20729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T18:00:18Z","cross_cats_sorted":["astro-ph.CO","cs.AI","hep-ph","hep-th"],"title_canon_sha256":"475576ede13ae2e271703615b3af73692433fad11a2d8ab1d4625c75a6d5d915","abstract_canon_sha256":"24d65d91da905bf0681d80e492bc2e1a095e2cc83b9d4bfef56583cc8def53b7"},"schema_version":"1.0"},"canonical_sha256":"7cb2a60925ed888f9efb681ef372cad929a3fad2e135af0a490e77cdce8b7847","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:32.907528Z","signature_b64":"dgluECEHNHMdXOLOPSrTR+yKafvSgisdgafhhpx2cuyB84mmQGtMSz+qcwbNc8+IWCSSUkarzs4Dybz7XJoTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cb2a60925ed888f9efb681ef372cad929a3fad2e135af0a490e77cdce8b7847","last_reissued_at":"2026-07-05T11:27:32.906985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:32.906985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.20729","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":"2026-07-05T11:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s7j+HhpiO2JxdruL+zivflS9jiZ8Mtfq1opiOUWeglRZL8kikE4vTtFE5Dqy8BaaINsIj9DhvlBuxSHozpDaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:07:25.203670Z"},"content_sha256":"f3e7b7edce0957b75cf9cf05db46a74a16b9acb1a334f67f1bae0bff8927fb5b","schema_version":"1.0","event_id":"sha256:f3e7b7edce0957b75cf9cf05db46a74a16b9acb1a334f67f1bae0bff8927fb5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PSZKMCJF5WEI7HX3NAPPG4WK3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test-time Scaling Techniques in Theoretical Physics -- A Comparison of Methods on the TPBench Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.CO","cs.AI","hep-ph","hep-th"],"primary_cat":"cs.LG","authors_text":"Daniel J.H. Chung, Frederic Sala, Maja Rudolph, Moritz M\\\"unchmeyer, Sai Chaitanya Tadepalli, Tianyi Li, Yurii Kvasiuk, Zhiqi Gao","submitted_at":"2025-06-25T18:00:18Z","abstract_excerpt":"Large language models (LLMs) have shown strong capabilities in complex reasoning, and test-time scaling techniques can enhance their performance with comparably low cost. Many of these methods have been developed and evaluated on mathematical reasoning benchmarks such as AIME. This paper investigates whether the lessons learned from these benchmarks generalize to the domain of advanced theoretical physics. We evaluate a range of common test-time scaling methods on the TPBench physics dataset and compare their effectiveness with results on AIME. To better leverage the structure of physics probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20729","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/2506.20729/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z2JmmHPfs0hvMqv4m4VXeOGZPc2682oj1WYiTIFcLWGUYJTU42yzuoGLDTN9MFhFAv8emzgRhwUFTFmlHAryBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:07:25.204290Z"},"content_sha256":"1c1866ddc6ce49b60669e62e9abcbea2227edf0bf50ac05737a27314422c734f","schema_version":"1.0","event_id":"sha256:1c1866ddc6ce49b60669e62e9abcbea2227edf0bf50ac05737a27314422c734f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PSZKMCJF5WEI7HX3NAPPG4WK3E/bundle.json","state_url":"https://pith.science/pith/PSZKMCJF5WEI7HX3NAPPG4WK3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PSZKMCJF5WEI7HX3NAPPG4WK3E/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":"2026-08-05T05:07:25Z","links":{"resolver":"https://pith.science/pith/PSZKMCJF5WEI7HX3NAPPG4WK3E","bundle":"https://pith.science/pith/PSZKMCJF5WEI7HX3NAPPG4WK3E/bundle.json","state":"https://pith.science/pith/PSZKMCJF5WEI7HX3NAPPG4WK3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PSZKMCJF5WEI7HX3NAPPG4WK3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PSZKMCJF5WEI7HX3NAPPG4WK3E","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":"24d65d91da905bf0681d80e492bc2e1a095e2cc83b9d4bfef56583cc8def53b7","cross_cats_sorted":["astro-ph.CO","cs.AI","hep-ph","hep-th"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T18:00:18Z","title_canon_sha256":"475576ede13ae2e271703615b3af73692433fad11a2d8ab1d4625c75a6d5d915"},"schema_version":"1.0","source":{"id":"2506.20729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20729","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20729v1","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20729","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"PSZKMCJF5WEI","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"PSZKMCJF5WEI7HX3","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"PSZKMCJF","created_at":"2026-07-05T11:27:32Z"}],"graph_snapshots":[{"event_id":"sha256:1c1866ddc6ce49b60669e62e9abcbea2227edf0bf50ac05737a27314422c734f","target":"graph","created_at":"2026-07-05T11:27:32Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.20729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown strong capabilities in complex reasoning, and test-time scaling techniques can enhance their performance with comparably low cost. Many of these methods have been developed and evaluated on mathematical reasoning benchmarks such as AIME. This paper investigates whether the lessons learned from these benchmarks generalize to the domain of advanced theoretical physics. We evaluate a range of common test-time scaling methods on the TPBench physics dataset and compare their effectiveness with results on AIME. To better leverage the structure of physics probl","authors_text":"Daniel J.H. Chung, Frederic Sala, Maja Rudolph, Moritz M\\\"unchmeyer, Sai Chaitanya Tadepalli, Tianyi Li, Yurii Kvasiuk, Zhiqi Gao","cross_cats":["astro-ph.CO","cs.AI","hep-ph","hep-th"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T18:00:18Z","title":"Test-time Scaling Techniques in Theoretical Physics -- A Comparison of Methods on the TPBench Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20729","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f3e7b7edce0957b75cf9cf05db46a74a16b9acb1a334f67f1bae0bff8927fb5b","target":"record","created_at":"2026-07-05T11:27:32Z","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":"24d65d91da905bf0681d80e492bc2e1a095e2cc83b9d4bfef56583cc8def53b7","cross_cats_sorted":["astro-ph.CO","cs.AI","hep-ph","hep-th"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T18:00:18Z","title_canon_sha256":"475576ede13ae2e271703615b3af73692433fad11a2d8ab1d4625c75a6d5d915"},"schema_version":"1.0","source":{"id":"2506.20729","kind":"arxiv","version":1}},"canonical_sha256":"7cb2a60925ed888f9efb681ef372cad929a3fad2e135af0a490e77cdce8b7847","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cb2a60925ed888f9efb681ef372cad929a3fad2e135af0a490e77cdce8b7847","first_computed_at":"2026-07-05T11:27:32.906985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:32.906985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dgluECEHNHMdXOLOPSrTR+yKafvSgisdgafhhpx2cuyB84mmQGtMSz+qcwbNc8+IWCSSUkarzs4Dybz7XJoTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:32.907528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3e7b7edce0957b75cf9cf05db46a74a16b9acb1a334f67f1bae0bff8927fb5b","sha256:1c1866ddc6ce49b60669e62e9abcbea2227edf0bf50ac05737a27314422c734f"],"state_sha256":"bab8258f637701ef9daab2ea2eb6fc5d46c61891d4a12cbf9796bad07458cda9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zI7OwUwJ7HFvOdtpv43tRQaA7ttPQOyVxsP42BYj+Sbcms3yF39faFaQ5DQx2IAE+nxeDd8X/kzGZAebXq5dBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:07:25.209674Z","bundle_sha256":"1bff4d355d9e11b0eacb6cb9673704e9fc0e13a0ada120a4651f3c6ccff8320e"}}