{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KYLULEUHUWE3R6TYOOHKGL5FIW","short_pith_number":"pith:KYLULEUH","canonical_record":{"source":{"id":"2506.11237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-12T19:15:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"79ca1da733b892e644a90dfc6902e53ce292817bedb4a036a8d25d981af00ce4","abstract_canon_sha256":"f87de29bb4c8d3d38df9c31a4f807c1ade89b6cf82c5b41595da5d36c899f252"},"schema_version":"1.0"},"canonical_sha256":"5617459287a589b8fa78738ea32fa545b65744067daf3360d92b971c1558242e","source":{"kind":"arxiv","id":"2506.11237","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11237","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11237v1","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11237","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_12","alias_value":"KYLULEUHUWE3","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_16","alias_value":"KYLULEUHUWE3R6TY","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_8","alias_value":"KYLULEUH","created_at":"2026-07-05T11:21:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KYLULEUHUWE3R6TYOOHKGL5FIW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-12T19:15:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"79ca1da733b892e644a90dfc6902e53ce292817bedb4a036a8d25d981af00ce4","abstract_canon_sha256":"f87de29bb4c8d3d38df9c31a4f807c1ade89b6cf82c5b41595da5d36c899f252"},"schema_version":"1.0"},"canonical_sha256":"5617459287a589b8fa78738ea32fa545b65744067daf3360d92b971c1558242e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:01.515944Z","signature_b64":"e5DjhynOQWBq8iGs9dE+3rcpAApEZwkYpJuWgWTq/81f0xdfiQ5vvKiTAJa6E2Sh4vFMa+iklCH9w9mS+kh4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5617459287a589b8fa78738ea32fa545b65744067daf3360d92b971c1558242e","last_reissued_at":"2026-07-05T11:21:01.515488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:01.515488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11237","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":"2026-07-05T11:21:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TdNNRf5BsIMtFph1af8uHAeHmwlezafnOwhoxcrH47ZgIZ16rAz3GkANJnL/QgFb5gmKUtN3ATara2dHYxZ4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:48:52.633222Z"},"content_sha256":"aafdf8105ceadee678846726a6afb70c43237781030d29dff51ed565bb824398","schema_version":"1.0","event_id":"sha256:aafdf8105ceadee678846726a6afb70c43237781030d29dff51ed565bb824398"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KYLULEUHUWE3R6TYOOHKGL5FIW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Brent Paulovicks, Ngoc Phuoc An Vo, Vadim Sheinin","submitted_at":"2025-06-12T19:15:05Z","abstract_excerpt":"In an effort to automatically evaluate and select the best model and improve code quality for automatic incident remediation in IT Automation, it is crucial to verify if the generated code for remediation action is syntactically and semantically correct and whether it can be executed correctly as intended. There are three approaches: 1) conventional methods use surface form similarity metrics (token match, exact match, etc.) which have numerous limitations, 2) execution-based evaluation focuses more on code functionality based on pass/fail judgments for given test-cases, and 3) LLM-as-a-Judge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11237","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/2506.11237/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":"2026-07-05T11:21:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tUOz9oKXQjk355wLiFVKAP9wKnpVr9Sx/P59wRri8EnqtvRdxFV/mKTddx4tv2TgMfgGJS7Hda+BD/VZpsdtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:48:52.633736Z"},"content_sha256":"b276e874fe565fe99a6882a839cf74d2fb1e7a8cfb79d89e2ca8a4b6e8c5e972","schema_version":"1.0","event_id":"sha256:b276e874fe565fe99a6882a839cf74d2fb1e7a8cfb79d89e2ca8a4b6e8c5e972"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYLULEUHUWE3R6TYOOHKGL5FIW/bundle.json","state_url":"https://pith.science/pith/KYLULEUHUWE3R6TYOOHKGL5FIW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYLULEUHUWE3R6TYOOHKGL5FIW/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":"2026-08-08T11:48:52Z","links":{"resolver":"https://pith.science/pith/KYLULEUHUWE3R6TYOOHKGL5FIW","bundle":"https://pith.science/pith/KYLULEUHUWE3R6TYOOHKGL5FIW/bundle.json","state":"https://pith.science/pith/KYLULEUHUWE3R6TYOOHKGL5FIW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYLULEUHUWE3R6TYOOHKGL5FIW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KYLULEUHUWE3R6TYOOHKGL5FIW","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":"f87de29bb4c8d3d38df9c31a4f807c1ade89b6cf82c5b41595da5d36c899f252","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-12T19:15:05Z","title_canon_sha256":"79ca1da733b892e644a90dfc6902e53ce292817bedb4a036a8d25d981af00ce4"},"schema_version":"1.0","source":{"id":"2506.11237","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11237","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11237v1","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11237","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_12","alias_value":"KYLULEUHUWE3","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_16","alias_value":"KYLULEUHUWE3R6TY","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_8","alias_value":"KYLULEUH","created_at":"2026-07-05T11:21:01Z"}],"graph_snapshots":[{"event_id":"sha256:b276e874fe565fe99a6882a839cf74d2fb1e7a8cfb79d89e2ca8a4b6e8c5e972","target":"graph","created_at":"2026-07-05T11:21:01Z","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/2506.11237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In an effort to automatically evaluate and select the best model and improve code quality for automatic incident remediation in IT Automation, it is crucial to verify if the generated code for remediation action is syntactically and semantically correct and whether it can be executed correctly as intended. There are three approaches: 1) conventional methods use surface form similarity metrics (token match, exact match, etc.) which have numerous limitations, 2) execution-based evaluation focuses more on code functionality based on pass/fail judgments for given test-cases, and 3) LLM-as-a-Judge ","authors_text":"Brent Paulovicks, Ngoc Phuoc An Vo, Vadim Sheinin","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-12T19:15:05Z","title":"LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11237","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:aafdf8105ceadee678846726a6afb70c43237781030d29dff51ed565bb824398","target":"record","created_at":"2026-07-05T11:21:01Z","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":"f87de29bb4c8d3d38df9c31a4f807c1ade89b6cf82c5b41595da5d36c899f252","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-12T19:15:05Z","title_canon_sha256":"79ca1da733b892e644a90dfc6902e53ce292817bedb4a036a8d25d981af00ce4"},"schema_version":"1.0","source":{"id":"2506.11237","kind":"arxiv","version":1}},"canonical_sha256":"5617459287a589b8fa78738ea32fa545b65744067daf3360d92b971c1558242e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5617459287a589b8fa78738ea32fa545b65744067daf3360d92b971c1558242e","first_computed_at":"2026-07-05T11:21:01.515488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:01.515488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e5DjhynOQWBq8iGs9dE+3rcpAApEZwkYpJuWgWTq/81f0xdfiQ5vvKiTAJa6E2Sh4vFMa+iklCH9w9mS+kh4AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:01.515944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11237","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aafdf8105ceadee678846726a6afb70c43237781030d29dff51ed565bb824398","sha256:b276e874fe565fe99a6882a839cf74d2fb1e7a8cfb79d89e2ca8a4b6e8c5e972"],"state_sha256":"dbbd0c5523616880fb1aa74b74331a510de65a5d9d8d16af911104ce79c9c42e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJBfqpTrSbawyHKDa4P3KPcuKMWNMyFZW8KDl1bN1zWhdbYaWuMmrnJ6mXIfV7JGzFCdcOOs8fEA3qHUTU0sAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:48:52.637857Z","bundle_sha256":"ff50ad03bcdada4e4f600ee4ab773d441a48204d0d103ba28bde3403dab19860"}}