{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KMUGPFEOAXW7CUMLPI2AP7KBXK","short_pith_number":"pith:KMUGPFEO","canonical_record":{"source":{"id":"2607.02440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T17:10:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a78c239c4395ec92c4694eed7967b7f4b8023a4d8555c302777c3814ff30fe20","abstract_canon_sha256":"f2b51a35fc08c3be704d4a97c1e6d7c6700a3965c7b3a14d818477a8e91c139b"},"schema_version":"1.0"},"canonical_sha256":"532867948e05edf1518b7a3407fd41ba9e4e5bfe2262e59b244ae2b4a3d8de80","source":{"kind":"arxiv","id":"2607.02440","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02440","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02440v1","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02440","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"KMUGPFEOAXW7","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"KMUGPFEOAXW7CUML","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"KMUGPFEO","created_at":"2026-07-03T01:17:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KMUGPFEOAXW7CUMLPI2AP7KBXK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.02440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T17:10:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a78c239c4395ec92c4694eed7967b7f4b8023a4d8555c302777c3814ff30fe20","abstract_canon_sha256":"f2b51a35fc08c3be704d4a97c1e6d7c6700a3965c7b3a14d818477a8e91c139b"},"schema_version":"1.0"},"canonical_sha256":"532867948e05edf1518b7a3407fd41ba9e4e5bfe2262e59b244ae2b4a3d8de80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:59.318950Z","signature_b64":"mjloDTJ4iCxFucZN+A7sIqxkgI+DQE1dXhRrQgkUGy4xxYBbejL2AoewidhyKsKNPIRLr36dk8/j2WNEHlXyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"532867948e05edf1518b7a3407fd41ba9e4e5bfe2262e59b244ae2b4a3d8de80","last_reissued_at":"2026-07-03T01:17:59.318568Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:59.318568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.02440","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-03T01:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lIiv+BH+Rdx4BihBZaDWHzQODnZhtjvzvI81+CmyTsVLPCkvb0iho6st0Da35dnU6s3+V0YV40XHH9cSBQjPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:05:43.369169Z"},"content_sha256":"2576a512d9445c899349e8156acf260cc584362e0a680bb2db8e4dbdb8be795a","schema_version":"1.0","event_id":"sha256:2576a512d9445c899349e8156acf260cc584362e0a680bb2db8e4dbdb8be795a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KMUGPFEOAXW7CUMLPI2AP7KBXK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Derek F. Wong, Guanjie Chen, Han Song, Jiacheng Chen, Jusen Du, Qingyu Yin, Runzhe Zhan, Tianle Li, Tong Zhu, Yafu Li, Yang Yang, Yanshu Li, Yu Cheng, Yulun Wu, Zhennan Shen, Zhilin Wang","submitted_at":"2026-07-02T17:10:13Z","abstract_excerpt":"Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended software-engineering progress. We introduce Autonomous Policy Evolution, a controlled evaluation setting in which a harness-model agent repeatedly edits an executable policy system under a fixed interaction budget. We instantiate this setting in EvoPolicyGym, a benchmark built from compact interactive RL environments that evaluates how agents iteratively improve explored policies. On the EvoPolicyGym "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02440","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/2607.02440/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":"2026-07-03T01:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/epMQFtdgzDhDBT5MWNIcMRhqJFEfJkXWItE5loO9937Wxfwi9mMGpMAMLRrrJZwtyqmhfr3uP5JLPjQ+JuVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:05:43.369557Z"},"content_sha256":"64bb10e7abe51e993bf7e27862b3690006af074fff65f7d9fbb141601eee187b","schema_version":"1.0","event_id":"sha256:64bb10e7abe51e993bf7e27862b3690006af074fff65f7d9fbb141601eee187b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KMUGPFEOAXW7CUMLPI2AP7KBXK/bundle.json","state_url":"https://pith.science/pith/KMUGPFEOAXW7CUMLPI2AP7KBXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KMUGPFEOAXW7CUMLPI2AP7KBXK/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":"2026-07-07T04:05:43Z","links":{"resolver":"https://pith.science/pith/KMUGPFEOAXW7CUMLPI2AP7KBXK","bundle":"https://pith.science/pith/KMUGPFEOAXW7CUMLPI2AP7KBXK/bundle.json","state":"https://pith.science/pith/KMUGPFEOAXW7CUMLPI2AP7KBXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KMUGPFEOAXW7CUMLPI2AP7KBXK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KMUGPFEOAXW7CUMLPI2AP7KBXK","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":"f2b51a35fc08c3be704d4a97c1e6d7c6700a3965c7b3a14d818477a8e91c139b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T17:10:13Z","title_canon_sha256":"a78c239c4395ec92c4694eed7967b7f4b8023a4d8555c302777c3814ff30fe20"},"schema_version":"1.0","source":{"id":"2607.02440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02440","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02440v1","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02440","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"KMUGPFEOAXW7","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"KMUGPFEOAXW7CUML","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"KMUGPFEO","created_at":"2026-07-03T01:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:64bb10e7abe51e993bf7e27862b3690006af074fff65f7d9fbb141601eee187b","target":"graph","created_at":"2026-07-03T01:17:59Z","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/2607.02440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended software-engineering progress. We introduce Autonomous Policy Evolution, a controlled evaluation setting in which a harness-model agent repeatedly edits an executable policy system under a fixed interaction budget. We instantiate this setting in EvoPolicyGym, a benchmark built from compact interactive RL environments that evaluates how agents iteratively improve explored policies. On the EvoPolicyGym ","authors_text":"Derek F. Wong, Guanjie Chen, Han Song, Jiacheng Chen, Jusen Du, Qingyu Yin, Runzhe Zhan, Tianle Li, Tong Zhu, Yafu Li, Yang Yang, Yanshu Li, Yu Cheng, Yulun Wu, Zhennan Shen, Zhilin Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T17:10:13Z","title":"EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02440","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":"sha256:2576a512d9445c899349e8156acf260cc584362e0a680bb2db8e4dbdb8be795a","target":"record","created_at":"2026-07-03T01:17:59Z","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":"f2b51a35fc08c3be704d4a97c1e6d7c6700a3965c7b3a14d818477a8e91c139b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T17:10:13Z","title_canon_sha256":"a78c239c4395ec92c4694eed7967b7f4b8023a4d8555c302777c3814ff30fe20"},"schema_version":"1.0","source":{"id":"2607.02440","kind":"arxiv","version":1}},"canonical_sha256":"532867948e05edf1518b7a3407fd41ba9e4e5bfe2262e59b244ae2b4a3d8de80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"532867948e05edf1518b7a3407fd41ba9e4e5bfe2262e59b244ae2b4a3d8de80","first_computed_at":"2026-07-03T01:17:59.318568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:59.318568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mjloDTJ4iCxFucZN+A7sIqxkgI+DQE1dXhRrQgkUGy4xxYBbejL2AoewidhyKsKNPIRLr36dk8/j2WNEHlXyBw==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:59.318950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2576a512d9445c899349e8156acf260cc584362e0a680bb2db8e4dbdb8be795a","sha256:64bb10e7abe51e993bf7e27862b3690006af074fff65f7d9fbb141601eee187b"],"state_sha256":"8eeac7be6231c3dfe8c5c02c3f63beb60b3d7cda6e8c04023f70986a470a8be3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4V5+ufp8atmXiD3oH+6lGwWf28uhFD74sTCnYwGLs3o08ElL1+x6C/EorU2mbKPKXUVqTc1Y2CLRE1SzU4PlAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:05:43.371503Z","bundle_sha256":"39aa42bb7f05e3a393012296a9dd5b1effb4bedd983140ba6e8fc37267b51eac"}}