{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:76HG23IF2J3HKAJLGQZQOUEERP","short_pith_number":"pith:76HG23IF","canonical_record":{"source":{"id":"2306.06808","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-11T23:53:29Z","cross_cats_sorted":[],"title_canon_sha256":"2d04c78c56a6138e12cad4135ccd7649a874485408ea45a22385690d4d2911b6","abstract_canon_sha256":"546ffb0135f09ef957dcfa144b69d5e637ec158963d26487e45ee8a66118f783"},"schema_version":"1.0"},"canonical_sha256":"ff8e6d6d05d27675012b34330750848bcc89137fd78b022e4e956326dd1d5b8d","source":{"kind":"arxiv","id":"2306.06808","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06808","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06808v2","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06808","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"76HG23IF2J3H","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"76HG23IF2J3HKAJL","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"76HG23IF","created_at":"2026-07-05T07:03:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:76HG23IF2J3HKAJLGQZQOUEERP","target":"record","payload":{"canonical_record":{"source":{"id":"2306.06808","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-11T23:53:29Z","cross_cats_sorted":[],"title_canon_sha256":"2d04c78c56a6138e12cad4135ccd7649a874485408ea45a22385690d4d2911b6","abstract_canon_sha256":"546ffb0135f09ef957dcfa144b69d5e637ec158963d26487e45ee8a66118f783"},"schema_version":"1.0"},"canonical_sha256":"ff8e6d6d05d27675012b34330750848bcc89137fd78b022e4e956326dd1d5b8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:28.227550Z","signature_b64":"Cuvo6Bm1UhRDg7IA2oQRzAuRbSBjEIezSt8jkZ0UL1VeSxDzuCAIyu6zIMAQETz3fFyCfaHTNOZW05aj9Wp2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff8e6d6d05d27675012b34330750848bcc89137fd78b022e4e956326dd1d5b8d","last_reissued_at":"2026-07-05T07:03:28.227005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:28.227005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.06808","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:03:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DOfJBFhMAb+vOGMtn4BvCsKmBuObxlr5Shx9PGgpPvg69OaPIq6eeo65IcBem/nUXTD55Q0RAzgibhGy+xB9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:51:04.876244Z"},"content_sha256":"81fde5110059eac6e36ef1517f4a11e8e1aea6edf171fdc38592e47e4de922f1","schema_version":"1.0","event_id":"sha256:81fde5110059eac6e36ef1517f4a11e8e1aea6edf171fdc38592e47e4de922f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:76HG23IF2J3HKAJLGQZQOUEERP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Miao, Jiangwei Wang, Meiyi Ma, Rahul Mangharam, Shuo Yang, Songyang Han, Zhili Zhang, Ziyan An","submitted_at":"2023-06-11T23:53:29Z","abstract_excerpt":"Reward design is a key component of deep reinforcement learning, yet some tasks and designer's objectives may be unnatural to define as a scalar cost function. Among the various techniques, formal methods integrated with DRL have garnered considerable attention due to their expressiveness and flexibility to define the reward and requirements for different states and actions of the agent. However, how to leverage Signal Temporal Logic (STL) to guide multi-agent reinforcement learning reward design remains unexplored. Complex interactions, heterogeneous goals and critical safety requirements in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06808","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/2306.06808/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":"2026-07-05T07:03:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IsM+L1IWIZWg+Hp6i8yg3icvFzhp6EkBUAPmk0iDzINrTrYoTPWm1vMT8geV6erY1YwCHB88j1EZ3sgdnuUNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:51:04.876615Z"},"content_sha256":"56a476695147ff798f4e7aabc9f4b109545b02631314d918752442fdd9babc1c","schema_version":"1.0","event_id":"sha256:56a476695147ff798f4e7aabc9f4b109545b02631314d918752442fdd9babc1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76HG23IF2J3HKAJLGQZQOUEERP/bundle.json","state_url":"https://pith.science/pith/76HG23IF2J3HKAJLGQZQOUEERP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76HG23IF2J3HKAJLGQZQOUEERP/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":"2026-07-07T06:51:04Z","links":{"resolver":"https://pith.science/pith/76HG23IF2J3HKAJLGQZQOUEERP","bundle":"https://pith.science/pith/76HG23IF2J3HKAJLGQZQOUEERP/bundle.json","state":"https://pith.science/pith/76HG23IF2J3HKAJLGQZQOUEERP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76HG23IF2J3HKAJLGQZQOUEERP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:76HG23IF2J3HKAJLGQZQOUEERP","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":"546ffb0135f09ef957dcfa144b69d5e637ec158963d26487e45ee8a66118f783","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-11T23:53:29Z","title_canon_sha256":"2d04c78c56a6138e12cad4135ccd7649a874485408ea45a22385690d4d2911b6"},"schema_version":"1.0","source":{"id":"2306.06808","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06808","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06808v2","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06808","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"76HG23IF2J3H","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"76HG23IF2J3HKAJL","created_at":"2026-07-05T07:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"76HG23IF","created_at":"2026-07-05T07:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:56a476695147ff798f4e7aabc9f4b109545b02631314d918752442fdd9babc1c","target":"graph","created_at":"2026-07-05T07:03:28Z","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/2306.06808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward design is a key component of deep reinforcement learning, yet some tasks and designer's objectives may be unnatural to define as a scalar cost function. Among the various techniques, formal methods integrated with DRL have garnered considerable attention due to their expressiveness and flexibility to define the reward and requirements for different states and actions of the agent. However, how to leverage Signal Temporal Logic (STL) to guide multi-agent reinforcement learning reward design remains unexplored. Complex interactions, heterogeneous goals and critical safety requirements in ","authors_text":"Fei Miao, Jiangwei Wang, Meiyi Ma, Rahul Mangharam, Shuo Yang, Songyang Han, Zhili Zhang, Ziyan An","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-11T23:53:29Z","title":"Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06808","kind":"arxiv","version":2},"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":"sha256:81fde5110059eac6e36ef1517f4a11e8e1aea6edf171fdc38592e47e4de922f1","target":"record","created_at":"2026-07-05T07:03:28Z","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":"546ffb0135f09ef957dcfa144b69d5e637ec158963d26487e45ee8a66118f783","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-11T23:53:29Z","title_canon_sha256":"2d04c78c56a6138e12cad4135ccd7649a874485408ea45a22385690d4d2911b6"},"schema_version":"1.0","source":{"id":"2306.06808","kind":"arxiv","version":2}},"canonical_sha256":"ff8e6d6d05d27675012b34330750848bcc89137fd78b022e4e956326dd1d5b8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff8e6d6d05d27675012b34330750848bcc89137fd78b022e4e956326dd1d5b8d","first_computed_at":"2026-07-05T07:03:28.227005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:28.227005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cuvo6Bm1UhRDg7IA2oQRzAuRbSBjEIezSt8jkZ0UL1VeSxDzuCAIyu6zIMAQETz3fFyCfaHTNOZW05aj9Wp2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:28.227550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06808","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81fde5110059eac6e36ef1517f4a11e8e1aea6edf171fdc38592e47e4de922f1","sha256:56a476695147ff798f4e7aabc9f4b109545b02631314d918752442fdd9babc1c"],"state_sha256":"f83669c859b579afe4ff2a1b7fa1cad552eed0fcc0e15ee61eafcc94421a0034"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PBzAH3GO3g5VM4Jrj7TsMHO9P1/VgWOQWkAJ2CAjfNC8xcEdbynyJwLPlqBGAkOcF+jBIKJFvQNIStOXOvTYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:51:04.878539Z","bundle_sha256":"a1f320b1b56cc3053857c30d9dd0716098ba1ad9850e16a67ac8c40223578fdd"}}