{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LPJKLDNSS2K4EQUV7LXLQ7Q3FM","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":"5563695530cdfe434dcb19edc9737b14a07f2593ec3fd40114b989a791a8ba9d","cross_cats_sorted":["cs.AI","cs.FL","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T01:16:42Z","title_canon_sha256":"a42b13b44fd40d06e99d7213ae24b56e07a3d51bb48f42de313a6cfe93d4d48d"},"schema_version":"1.0","source":{"id":"2304.12508","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12508","created_at":"2026-07-05T06:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12508v1","created_at":"2026-07-05T06:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12508","created_at":"2026-07-05T06:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"LPJKLDNSS2K4","created_at":"2026-07-05T06:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"LPJKLDNSS2K4EQUV","created_at":"2026-07-05T06:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"LPJKLDNS","created_at":"2026-07-05T06:04:17Z"}],"graph_snapshots":[{"event_id":"sha256:f64ea2b295d1c7c93fbecf6629c9cefe073f6acc36778da198ff3314a68ac712","target":"graph","created_at":"2026-07-05T06:04:17Z","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/2304.12508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a model-free reinforcement learning solution, namely the ASAP-Phi framework, to encourage an agent to fulfill a formal specification ASAP. The framework leverages a piece-wise reward function that assigns quantitative semantic reward to traces not satisfying the specification, and a high constant reward to the remaining. Then, it trains an agent with an actor-critic-based algorithm, such as soft actor-critic (SAC), or deep deterministic policy gradient (DDPG). Moreover, we prove that ASAP-Phi produces policies that prioritize fulfilling a specification ASAP. Extensive experiments ar","authors_text":"Fanxin Kong, Insup Lee, Mengyu Liu, Oleg Sokolsky, Pengyuan Lu, Xin Chen","cross_cats":["cs.AI","cs.FL","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T01:16:42Z","title":"Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12508","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":"sha256:086d588434958733917ec6e98f689ccea397f067673e0c4324b8d498c61e4b45","target":"record","created_at":"2026-07-05T06:04:17Z","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":"5563695530cdfe434dcb19edc9737b14a07f2593ec3fd40114b989a791a8ba9d","cross_cats_sorted":["cs.AI","cs.FL","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T01:16:42Z","title_canon_sha256":"a42b13b44fd40d06e99d7213ae24b56e07a3d51bb48f42de313a6cfe93d4d48d"},"schema_version":"1.0","source":{"id":"2304.12508","kind":"arxiv","version":1}},"canonical_sha256":"5bd2a58db29695c24295faeeb87e1b2b0a8115d2f4885bbf54ebca3a0e213257","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bd2a58db29695c24295faeeb87e1b2b0a8115d2f4885bbf54ebca3a0e213257","first_computed_at":"2026-07-05T06:04:17.639106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:17.639106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D8iKPWrWnHa3OksR50Zs4f5+2JgLwrEvVA+A0xI8otGUbJ5CmFLLIdz2iPIomMiFhmVOeVZkzqkgX1abTJpdBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:17.639603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.12508","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:086d588434958733917ec6e98f689ccea397f067673e0c4324b8d498c61e4b45","sha256:f64ea2b295d1c7c93fbecf6629c9cefe073f6acc36778da198ff3314a68ac712"],"state_sha256":"b94503fdfd1ad136407bd4a2900ce67e70187b681e193ae510b8979216b14785"}