{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B7YCEUYUF27GQ5WDWPJNSOUZEH","short_pith_number":"pith:B7YCEUYU","schema_version":"1.0","canonical_sha256":"0ff02253142ebe6876c3b3d2d93a9921d1681a5182deb28726fc7ad3d8963974","source":{"kind":"arxiv","id":"2111.04147","version":2},"attestation_state":"computed","paper":{"title":"Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.AI","authors_text":"Carl Trimbach, Daniel Ritter, Homer Walke, Michael Littman","submitted_at":"2021-11-07T18:51:02Z","abstract_excerpt":"Finite linear temporal logic ($\\mathsf{LTL}_f$) is a powerful formal representation for modeling temporal sequences. We address the problem of learning a compact $\\mathsf{LTL}_f$ formula from labeled traces of system behavior. We propose a novel neural network operator and evaluate the resulting architecture, Neural$\\mathsf{LTL}_f$. Our approach includes a specialized recurrent filter, designed to subsume $\\mathsf{LTL}_f$ temporal operators, to learn a highly accurate classifier for traces. Then, it discretizes the activations and extracts the truth table represented by the learned weights. Th"},"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":"2111.04147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-11-07T18:51:02Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"a819a4ec40e2a8bdb78d56d2351ca0afc2292c41c014eb88720fb40f53122fc6","abstract_canon_sha256":"067353c6d268ad7d0dcc1ac7293637676b292f9561838df2aae037c0116274ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:51.460181Z","signature_b64":"i1REvtTEJbomzP3112rKxZazpmwAQJAZhj/KBSJpsW+GhDUJqfALSa27SIY39h6BdSTHzPuqzVVQL5Uxgpk4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ff02253142ebe6876c3b3d2d93a9921d1681a5182deb28726fc7ad3d8963974","last_reissued_at":"2026-07-05T03:33:51.459801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:51.459801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.AI","authors_text":"Carl Trimbach, Daniel Ritter, Homer Walke, Michael Littman","submitted_at":"2021-11-07T18:51:02Z","abstract_excerpt":"Finite linear temporal logic ($\\mathsf{LTL}_f$) is a powerful formal representation for modeling temporal sequences. We address the problem of learning a compact $\\mathsf{LTL}_f$ formula from labeled traces of system behavior. We propose a novel neural network operator and evaluate the resulting architecture, Neural$\\mathsf{LTL}_f$. Our approach includes a specialized recurrent filter, designed to subsume $\\mathsf{LTL}_f$ temporal operators, to learn a highly accurate classifier for traces. Then, it discretizes the activations and extracts the truth table represented by the learned weights. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04147","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/2111.04147/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":"2111.04147","created_at":"2026-07-05T03:33:51.459852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.04147v2","created_at":"2026-07-05T03:33:51.459852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04147","created_at":"2026-07-05T03:33:51.459852+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7YCEUYUF27G","created_at":"2026-07-05T03:33:51.459852+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7YCEUYUF27GQ5WD","created_at":"2026-07-05T03:33:51.459852+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7YCEUYU","created_at":"2026-07-05T03:33:51.459852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02491","citing_title":"RNN Generalization to Omega-Regular Languages","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH","json":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH.json","graph_json":"https://pith.science/api/pith-number/B7YCEUYUF27GQ5WDWPJNSOUZEH/graph.json","events_json":"https://pith.science/api/pith-number/B7YCEUYUF27GQ5WDWPJNSOUZEH/events.json","paper":"https://pith.science/paper/B7YCEUYU"},"agent_actions":{"view_html":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH","download_json":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH.json","view_paper":"https://pith.science/paper/B7YCEUYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.04147&json=true","fetch_graph":"https://pith.science/api/pith-number/B7YCEUYUF27GQ5WDWPJNSOUZEH/graph.json","fetch_events":"https://pith.science/api/pith-number/B7YCEUYUF27GQ5WDWPJNSOUZEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH/action/storage_attestation","attest_author":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH/action/author_attestation","sign_citation":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH/action/citation_signature","submit_replication":"https://pith.science/pith/B7YCEUYUF27GQ5WDWPJNSOUZEH/action/replication_record"}},"created_at":"2026-07-05T03:33:51.459852+00:00","updated_at":"2026-07-05T03:33:51.459852+00:00"}