{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6DHBEE23T64OQIDWJ5E5FGTRUL","short_pith_number":"pith:6DHBEE23","schema_version":"1.0","canonical_sha256":"f0ce12135b9fb8e820764f49d29a71a2f9a40d8249f7268ec55c1ed073fb4045","source":{"kind":"arxiv","id":"2505.20658","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongshen Chen, Jie An, Naijun Zhan, Xiaohong Chen, Yue Fang, Zhi Jin","submitted_at":"2025-05-27T03:07:25Z","abstract_excerpt":"Temporal Logic (TL), especially Signal Temporal Logic (STL), enables precise formal specification, making it widely used in cyber-physical systems such as autonomous driving and robotics. Automatically transforming NL into STL is an attractive approach to overcome the limitations of manual transformation, which is time-consuming and error-prone. However, due to the lack of datasets, automatic transformation currently faces significant challenges and has not been fully explored. In this paper, we propose an NL-STL dataset named STL-Diversity-Enhanced (STL-DivEn), which comprises 16,000 samples "},"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":"2505.20658","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T03:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"3146d48a673054638438a2915764a3521b53450e1f5e68bd653a4b3d7f0c675f","abstract_canon_sha256":"85afd6d62c4084806134b0f88c184c78c4571306cc031b0f9d30edab1db66b5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:29.834942Z","signature_b64":"c5PaCcbCxs9v8hjcmrE4dJpXh65zpMbcHYKbn1XLEsrruokCusnjnvcL3m63hhjxQsmk+1pZdWF1tQ6706vpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ce12135b9fb8e820764f49d29a71a2f9a40d8249f7268ec55c1ed073fb4045","last_reissued_at":"2026-07-05T11:42:29.834444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:29.834444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongshen Chen, Jie An, Naijun Zhan, Xiaohong Chen, Yue Fang, Zhi Jin","submitted_at":"2025-05-27T03:07:25Z","abstract_excerpt":"Temporal Logic (TL), especially Signal Temporal Logic (STL), enables precise formal specification, making it widely used in cyber-physical systems such as autonomous driving and robotics. Automatically transforming NL into STL is an attractive approach to overcome the limitations of manual transformation, which is time-consuming and error-prone. However, due to the lack of datasets, automatic transformation currently faces significant challenges and has not been fully explored. In this paper, we propose an NL-STL dataset named STL-Diversity-Enhanced (STL-DivEn), which comprises 16,000 samples "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20658","kind":"arxiv","version":2},"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/2505.20658/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":"2505.20658","created_at":"2026-07-05T11:42:29.834511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20658v2","created_at":"2026-07-05T11:42:29.834511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20658","created_at":"2026-07-05T11:42:29.834511+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DHBEE23T64O","created_at":"2026-07-05T11:42:29.834511+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DHBEE23T64OQIDW","created_at":"2026-07-05T11:42:29.834511+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DHBEE23","created_at":"2026-07-05T11:42:29.834511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14582","citing_title":"BT-TL-DMPs: A Novel Robot TAMP Framework Combining Behavior Tree, Temporal Logic and Dynamical Movement Primitives","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL","json":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL.json","graph_json":"https://pith.science/api/pith-number/6DHBEE23T64OQIDWJ5E5FGTRUL/graph.json","events_json":"https://pith.science/api/pith-number/6DHBEE23T64OQIDWJ5E5FGTRUL/events.json","paper":"https://pith.science/paper/6DHBEE23"},"agent_actions":{"view_html":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL","download_json":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL.json","view_paper":"https://pith.science/paper/6DHBEE23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20658&json=true","fetch_graph":"https://pith.science/api/pith-number/6DHBEE23T64OQIDWJ5E5FGTRUL/graph.json","fetch_events":"https://pith.science/api/pith-number/6DHBEE23T64OQIDWJ5E5FGTRUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL/action/storage_attestation","attest_author":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL/action/author_attestation","sign_citation":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL/action/citation_signature","submit_replication":"https://pith.science/pith/6DHBEE23T64OQIDWJ5E5FGTRUL/action/replication_record"}},"created_at":"2026-07-05T11:42:29.834511+00:00","updated_at":"2026-07-05T11:42:29.834511+00:00"}