{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PGUNMLJKO3VDXZPHV6SOCFLNAG","short_pith_number":"pith:PGUNMLJK","schema_version":"1.0","canonical_sha256":"79a8d62d2a76ea3be5e7afa4e1156d01aa4b2de598eef622d61b6fc5d62a9bd5","source":{"kind":"arxiv","id":"2607.04784","version":1},"attestation_state":"computed","paper":{"title":"A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Haoyu Wang, Kailong Wang, Ling Shi, Shide Zhou","submitted_at":"2026-07-06T08:14:53Z","abstract_excerpt":"Defining the reasoning boundaries and ensuring the reliability of Large Reasoning Models (LRMs) remains a critical challenge. Current benchmarks primarily rely on static datasets susceptible to data contamination or synthetic tasks lacking fine-grained difficulty control. Furthermore, standard outcome-based evaluations often conceal reasoning flaws by neglecting the reasoning process.\n  To address these limitations, we introduce TRACE, a testing framework that models temporal reasoning as constraint satisfaction problems via Allen's Interval Algebra. This approach enables precise regulation of"},"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":"2607.04784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-06T08:14:53Z","cross_cats_sorted":[],"title_canon_sha256":"207082afc1d34b94d6e796ce95f0c114633129d691a59da123b7cc469e13ec7a","abstract_canon_sha256":"36f885b897748a07872c01720e567498ec24897d468b3d7c2b89a12a9b5324af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:03.115640Z","signature_b64":"JbFXdNN5cKvlO6+EA8fjmn/migSAkfrQuAeeUJg3G7AcryxaZD2Gwop+y6+YUJdsnm26RyuRTDA08CB0nZmTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79a8d62d2a76ea3be5e7afa4e1156d01aa4b2de598eef622d61b6fc5d62a9bd5","last_reissued_at":"2026-07-07T02:20:03.115026Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:03.115026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Haoyu Wang, Kailong Wang, Ling Shi, Shide Zhou","submitted_at":"2026-07-06T08:14:53Z","abstract_excerpt":"Defining the reasoning boundaries and ensuring the reliability of Large Reasoning Models (LRMs) remains a critical challenge. Current benchmarks primarily rely on static datasets susceptible to data contamination or synthetic tasks lacking fine-grained difficulty control. Furthermore, standard outcome-based evaluations often conceal reasoning flaws by neglecting the reasoning process.\n  To address these limitations, we introduce TRACE, a testing framework that models temporal reasoning as constraint satisfaction problems via Allen's Interval Algebra. This approach enables precise regulation of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04784","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/2607.04784/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":"2607.04784","created_at":"2026-07-07T02:20:03.115109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04784v1","created_at":"2026-07-07T02:20:03.115109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04784","created_at":"2026-07-07T02:20:03.115109+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGUNMLJKO3VD","created_at":"2026-07-07T02:20:03.115109+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGUNMLJKO3VDXZPH","created_at":"2026-07-07T02:20:03.115109+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGUNMLJK","created_at":"2026-07-07T02:20:03.115109+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG","json":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG.json","graph_json":"https://pith.science/api/pith-number/PGUNMLJKO3VDXZPHV6SOCFLNAG/graph.json","events_json":"https://pith.science/api/pith-number/PGUNMLJKO3VDXZPHV6SOCFLNAG/events.json","paper":"https://pith.science/paper/PGUNMLJK"},"agent_actions":{"view_html":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG","download_json":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG.json","view_paper":"https://pith.science/paper/PGUNMLJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04784&json=true","fetch_graph":"https://pith.science/api/pith-number/PGUNMLJKO3VDXZPHV6SOCFLNAG/graph.json","fetch_events":"https://pith.science/api/pith-number/PGUNMLJKO3VDXZPHV6SOCFLNAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG/action/storage_attestation","attest_author":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG/action/author_attestation","sign_citation":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG/action/citation_signature","submit_replication":"https://pith.science/pith/PGUNMLJKO3VDXZPHV6SOCFLNAG/action/replication_record"}},"created_at":"2026-07-07T02:20:03.115109+00:00","updated_at":"2026-07-07T02:20:03.115109+00:00"}