{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:24LDJL2TQ3M2O2CAASH362AG57","short_pith_number":"pith:24LDJL2T","canonical_record":{"source":{"id":"2605.09730","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-10T19:57:32Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"ccf23749a1292b2dbad90ba1feda00214e8796edd66e17274099458699cf2c6e","abstract_canon_sha256":"d8622bcaec8443429806e5c6c1146b1770b27141eabf9be38eb837912bb07ce9"},"schema_version":"1.0"},"canonical_sha256":"d71634af5386d9a76840048fbf6806efd7f792b4d4c5c15d26dc2bd2c693b728","source":{"kind":"arxiv","id":"2605.09730","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09730","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09730v3","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09730","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"pith_short_12","alias_value":"24LDJL2TQ3M2","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"pith_short_16","alias_value":"24LDJL2TQ3M2O2CA","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"pith_short_8","alias_value":"24LDJL2T","created_at":"2026-05-20T00:02:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:24LDJL2TQ3M2O2CAASH362AG57","target":"record","payload":{"canonical_record":{"source":{"id":"2605.09730","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-10T19:57:32Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"ccf23749a1292b2dbad90ba1feda00214e8796edd66e17274099458699cf2c6e","abstract_canon_sha256":"d8622bcaec8443429806e5c6c1146b1770b27141eabf9be38eb837912bb07ce9"},"schema_version":"1.0"},"canonical_sha256":"d71634af5386d9a76840048fbf6806efd7f792b4d4c5c15d26dc2bd2c693b728","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:12.785110Z","signature_b64":"zLIU/dW27f3NNohTB1pIoo/fqB9v8Pjx8uljAEfLToExUjFi90qFoeh/vk9wkSHlQRKYxpEWQ7K7XyzVYnIcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d71634af5386d9a76840048fbf6806efd7f792b4d4c5c15d26dc2bd2c693b728","last_reissued_at":"2026-05-20T00:02:12.784330Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:12.784330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.09730","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Msy8WzryYDM79C2AQs0yfHHk21eJ4igtZI8pX458oMQ69Mz134wGXl7UDdNMTbNmccBvlyUWcnhHpkS7VxHwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T01:16:32.850503Z"},"content_sha256":"2afa6b49a5baddf880e8e0f16d775a6faa136d2f77c8b3f9f5a54bc2b06b3f0d","schema_version":"1.0","event_id":"sha256:2afa6b49a5baddf880e8e0f16d775a6faa136d2f77c8b3f9f5a54bc2b06b3f0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:24LDJL2TQ3M2O2CAASH362AG57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RubricRefine generates task-specific rubrics to score and repair tool-use code for contract violations before any execution occurs.","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Abhay Venkatesh, Brendan Evers, Sam Saltwick, Will LeVine","submitted_at":"2026-05-10T19:57:32Z","abstract_excerpt":"Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structure of the feedback signal: unstructured critique helps inconsistently across models, and even revision with real execution feedback improves only modestly ($0.75$ vs. $0.65$ baseline). The dominant failures are inter-tool contract violations (wrong output shape, incorrect tool routing, broken argument provenance) that run to completion without raising errors, making runtime feedback insufficient. We introduce RubricRefine, a training-free method"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With zero execution attempts, RubricRefine reaches 0.86 on M3ToolEval averaged across seven models-improving over prior inference-time baselines on every model tested on this benchmark, at 2.6X lower latency than the strongest non-iterative alternative.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That inter-tool contract violations (wrong output shape, incorrect routing, broken argument provenance) are the dominant failures and that automatically generated rubrics can reliably detect them without any execution feedback or model-specific tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RubricRefine improves tool-use agent reliability to 0.86 on M3ToolEval by generating rubrics for pre-execution contract checking and iterative repair, outperforming baselines at 2.6X lower latency while showing no gain on single-step tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RubricRefine generates task-specific rubrics to score and repair tool-use code for contract violations before any execution occurs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2c948d2ed6f63b8e18f797103f76dd96673eb6bad91bf6f0212ec58c7af17181"},"source":{"id":"2605.09730","kind":"arxiv","version":3},"verdict":{"id":"c81479f9-594f-4201-9856-945bb3f71783","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:21:43.945619Z","strongest_claim":"With zero execution attempts, RubricRefine reaches 0.86 on M3ToolEval averaged across seven models-improving over prior inference-time baselines on every model tested on this benchmark, at 2.6X lower latency than the strongest non-iterative alternative.","one_line_summary":"RubricRefine improves tool-use agent reliability to 0.86 on M3ToolEval by generating rubrics for pre-execution contract checking and iterative repair, outperforming baselines at 2.6X lower latency while showing no gain on single-step tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That inter-tool contract violations (wrong output shape, incorrect routing, broken argument provenance) are the dominant failures and that automatically generated rubrics can reliably detect them without any execution feedback or model-specific tuning.","pith_extraction_headline":"RubricRefine generates task-specific rubrics to score and repair tool-use code for contract violations before any execution occurs."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.09730/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T16:37:11.934993Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T12:31:18.117618Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:59:29.735265Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9fea2bff5d0949ab4a9ea3e1e4d394c8ec88be24629387903ac983ee562c7d2d"},"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":"c81479f9-594f-4201-9856-945bb3f71783"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ic3GGCkScrfMawKnRvzzoy15trdkUPaycERmPv6/aWme5JVj88/8J3W8INtHYLkNY9S07iYGAq40rl8tR2I/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T01:16:32.850989Z"},"content_sha256":"3e6f76e44d05035f805d22fef1c4a62de76e72f0d4fc198ddc8e40425614d3c5","schema_version":"1.0","event_id":"sha256:3e6f76e44d05035f805d22fef1c4a62de76e72f0d4fc198ddc8e40425614d3c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24LDJL2TQ3M2O2CAASH362AG57/bundle.json","state_url":"https://pith.science/pith/24LDJL2TQ3M2O2CAASH362AG57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24LDJL2TQ3M2O2CAASH362AG57/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":"2026-07-10T01:16:32Z","links":{"resolver":"https://pith.science/pith/24LDJL2TQ3M2O2CAASH362AG57","bundle":"https://pith.science/pith/24LDJL2TQ3M2O2CAASH362AG57/bundle.json","state":"https://pith.science/pith/24LDJL2TQ3M2O2CAASH362AG57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24LDJL2TQ3M2O2CAASH362AG57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:24LDJL2TQ3M2O2CAASH362AG57","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":"d8622bcaec8443429806e5c6c1146b1770b27141eabf9be38eb837912bb07ce9","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-10T19:57:32Z","title_canon_sha256":"ccf23749a1292b2dbad90ba1feda00214e8796edd66e17274099458699cf2c6e"},"schema_version":"1.0","source":{"id":"2605.09730","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09730","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09730v3","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09730","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"pith_short_12","alias_value":"24LDJL2TQ3M2","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"pith_short_16","alias_value":"24LDJL2TQ3M2O2CA","created_at":"2026-05-20T00:02:12Z"},{"alias_kind":"pith_short_8","alias_value":"24LDJL2T","created_at":"2026-05-20T00:02:12Z"}],"graph_snapshots":[{"event_id":"sha256:3e6f76e44d05035f805d22fef1c4a62de76e72f0d4fc198ddc8e40425614d3c5","target":"graph","created_at":"2026-05-20T00:02:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"With zero execution attempts, RubricRefine reaches 0.86 on M3ToolEval averaged across seven models-improving over prior inference-time baselines on every model tested on this benchmark, at 2.6X lower latency than the strongest non-iterative alternative."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That inter-tool contract violations (wrong output shape, incorrect routing, broken argument provenance) are the dominant failures and that automatically generated rubrics can reliably detect them without any execution feedback or model-specific tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RubricRefine improves tool-use agent reliability to 0.86 on M3ToolEval by generating rubrics for pre-execution contract checking and iterative repair, outperforming baselines at 2.6X lower latency while showing no gain on single-step tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"RubricRefine generates task-specific rubrics to score and repair tool-use code for contract violations before any execution occurs."}],"snapshot_sha256":"2c948d2ed6f63b8e18f797103f76dd96673eb6bad91bf6f0212ec58c7af17181"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T16:37:11.934993Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T12:31:18.117618Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:59:29.735265Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.09730/integrity.json","findings":[],"snapshot_sha256":"9fea2bff5d0949ab4a9ea3e1e4d394c8ec88be24629387903ac983ee562c7d2d","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structure of the feedback signal: unstructured critique helps inconsistently across models, and even revision with real execution feedback improves only modestly ($0.75$ vs. $0.65$ baseline). The dominant failures are inter-tool contract violations (wrong output shape, incorrect tool routing, broken argument provenance) that run to completion without raising errors, making runtime feedback insufficient. We introduce RubricRefine, a training-free method","authors_text":"Abhay Venkatesh, Brendan Evers, Sam Saltwick, Will LeVine","cross_cats":["cs.SE"],"headline":"RubricRefine generates task-specific rubrics to score and repair tool-use code for contract violations before any execution occurs.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-10T19:57:32Z","title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.09730","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T05:21:43.945619Z","id":"c81479f9-594f-4201-9856-945bb3f71783","model_set":{"reader":"grok-4.3"},"one_line_summary":"RubricRefine improves tool-use agent reliability to 0.86 on M3ToolEval by generating rubrics for pre-execution contract checking and iterative repair, outperforming baselines at 2.6X lower latency while showing no gain on single-step tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"RubricRefine generates task-specific rubrics to score and repair tool-use code for contract violations before any execution occurs.","strongest_claim":"With zero execution attempts, RubricRefine reaches 0.86 on M3ToolEval averaged across seven models-improving over prior inference-time baselines on every model tested on this benchmark, at 2.6X lower latency than the strongest non-iterative alternative.","weakest_assumption":"That inter-tool contract violations (wrong output shape, incorrect routing, broken argument provenance) are the dominant failures and that automatically generated rubrics can reliably detect them without any execution feedback or model-specific tuning."}},"verdict_id":"c81479f9-594f-4201-9856-945bb3f71783"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2afa6b49a5baddf880e8e0f16d775a6faa136d2f77c8b3f9f5a54bc2b06b3f0d","target":"record","created_at":"2026-05-20T00:02:12Z","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":"d8622bcaec8443429806e5c6c1146b1770b27141eabf9be38eb837912bb07ce9","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-10T19:57:32Z","title_canon_sha256":"ccf23749a1292b2dbad90ba1feda00214e8796edd66e17274099458699cf2c6e"},"schema_version":"1.0","source":{"id":"2605.09730","kind":"arxiv","version":3}},"canonical_sha256":"d71634af5386d9a76840048fbf6806efd7f792b4d4c5c15d26dc2bd2c693b728","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d71634af5386d9a76840048fbf6806efd7f792b4d4c5c15d26dc2bd2c693b728","first_computed_at":"2026-05-20T00:02:12.784330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:12.784330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zLIU/dW27f3NNohTB1pIoo/fqB9v8Pjx8uljAEfLToExUjFi90qFoeh/vk9wkSHlQRKYxpEWQ7K7XyzVYnIcCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:12.785110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.09730","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2afa6b49a5baddf880e8e0f16d775a6faa136d2f77c8b3f9f5a54bc2b06b3f0d","sha256:3e6f76e44d05035f805d22fef1c4a62de76e72f0d4fc198ddc8e40425614d3c5"],"state_sha256":"eaff7d6ef5bb52701faa8e5ad26970c0db96d59bf9f86d46a4511b90e8422cb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JphPz2w7orlPbReGgtg+4luOlxcpZPUlUu47QzFUg8H0/77+Jdxw4TL/pa7+8KNAD/pzNI5DT+SIy+EaGS16BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T01:16:32.853189Z","bundle_sha256":"bd90c1bd713bc73c8dc4ae96e7473235a828813d20dfae633e2abc75153e89fe"}}