{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SWTKLERXNVY4XIBTACGT2IEKXE","short_pith_number":"pith:SWTKLERX","canonical_record":{"source":{"id":"2606.31435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T10:08:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1fc464a8bf97eb5267a7e68692ac5ffdabbc43bbff5cedbbd1c699dbfb27a90c","abstract_canon_sha256":"9c14278e13c7c08ef24150a4d86643ed90f6f3be8adfd58570a722203ab7f1f2"},"schema_version":"1.0"},"canonical_sha256":"95a6a592376d71cba033008d3d208ab900f59e6276a13c3a0b223de36024d6fc","source":{"kind":"arxiv","id":"2606.31435","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31435","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31435v1","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31435","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"SWTKLERXNVY4","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"SWTKLERXNVY4XIBT","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"SWTKLERX","created_at":"2026-07-01T01:18:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SWTKLERXNVY4XIBTACGT2IEKXE","target":"record","payload":{"canonical_record":{"source":{"id":"2606.31435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T10:08:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1fc464a8bf97eb5267a7e68692ac5ffdabbc43bbff5cedbbd1c699dbfb27a90c","abstract_canon_sha256":"9c14278e13c7c08ef24150a4d86643ed90f6f3be8adfd58570a722203ab7f1f2"},"schema_version":"1.0"},"canonical_sha256":"95a6a592376d71cba033008d3d208ab900f59e6276a13c3a0b223de36024d6fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:03.152978Z","signature_b64":"9+7ZWZ0PN8gf8UUwJNo8os2/QWO2Y19wpCFlNPWZ83i99RIlPA8NLLCpCIzF/a1qlLl9sOE8VYiPrtiyXk+QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a6a592376d71cba033008d3d208ab900f59e6276a13c3a0b223de36024d6fc","last_reissued_at":"2026-07-01T01:18:03.152553Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:03.152553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.31435","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":"2026-07-01T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wIX8wE36hGJyK/E6d259KUaLh64Gt/lPyQC3PJkzs3wTW8JQ07eZSNvXF2aZ9q7084G8WbbhwgONDLumSmfAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T17:49:27.789117Z"},"content_sha256":"6fec8ced6358b342a21e006fcd53947fbc7baa5ba214539f50b40d6ed603cc94","schema_version":"1.0","event_id":"sha256:6fec8ced6358b342a21e006fcd53947fbc7baa5ba214539f50b40d6ed603cc94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SWTKLERXNVY4XIBTACGT2IEKXE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Daoyuan Chen, Qianli Shen, Sijia Li, Xiang Li, Yaliang Li, Yi R. Fung, Yuchen Huang, Zhenqing Ling","submitted_at":"2026-06-30T10:08:45Z","abstract_excerpt":"Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome. While existing benchmarks either isolate text editing or entangle it with code and tool execution, it remains unclear whether LLMs can directly and faithfully execute these compositional, order-sensitive data refinement recipes. To fill this gap, we introduce CDR-Bench, a comprehensive benchmark featuring 3,462 high-quality tasks spanning four real-world data refinement domains and 29 distinct operators. Our benchmark evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31435","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/2606.31435/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":"2026-07-01T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7mEX3i/nL8rqe7J3MqllyEh+kThOqfmmZP23VwB4y11COZ9s9qgsIJDrDYiY1n99LX2SIBRiDng2Tobq3GN9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T17:49:27.789518Z"},"content_sha256":"58f0c1c80ac44a8f1b286bbe54e3cdd84c6ea53d980e85cc120bfcb449d377ff","schema_version":"1.0","event_id":"sha256:58f0c1c80ac44a8f1b286bbe54e3cdd84c6ea53d980e85cc120bfcb449d377ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWTKLERXNVY4XIBTACGT2IEKXE/bundle.json","state_url":"https://pith.science/pith/SWTKLERXNVY4XIBTACGT2IEKXE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWTKLERXNVY4XIBTACGT2IEKXE/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":"2026-07-03T17:49:27Z","links":{"resolver":"https://pith.science/pith/SWTKLERXNVY4XIBTACGT2IEKXE","bundle":"https://pith.science/pith/SWTKLERXNVY4XIBTACGT2IEKXE/bundle.json","state":"https://pith.science/pith/SWTKLERXNVY4XIBTACGT2IEKXE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWTKLERXNVY4XIBTACGT2IEKXE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SWTKLERXNVY4XIBTACGT2IEKXE","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":"9c14278e13c7c08ef24150a4d86643ed90f6f3be8adfd58570a722203ab7f1f2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T10:08:45Z","title_canon_sha256":"1fc464a8bf97eb5267a7e68692ac5ffdabbc43bbff5cedbbd1c699dbfb27a90c"},"schema_version":"1.0","source":{"id":"2606.31435","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31435","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31435v1","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31435","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"SWTKLERXNVY4","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"SWTKLERXNVY4XIBT","created_at":"2026-07-01T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"SWTKLERX","created_at":"2026-07-01T01:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:58f0c1c80ac44a8f1b286bbe54e3cdd84c6ea53d980e85cc120bfcb449d377ff","target":"graph","created_at":"2026-07-01T01:18:03Z","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/2606.31435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome. While existing benchmarks either isolate text editing or entangle it with code and tool execution, it remains unclear whether LLMs can directly and faithfully execute these compositional, order-sensitive data refinement recipes. To fill this gap, we introduce CDR-Bench, a comprehensive benchmark featuring 3,462 high-quality tasks spanning four real-world data refinement domains and 29 distinct operators. Our benchmark evaluat","authors_text":"Daoyuan Chen, Qianli Shen, Sijia Li, Xiang Li, Yaliang Li, Yi R. Fung, Yuchen Huang, Zhenqing Ling","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T10:08:45Z","title":"CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31435","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":"sha256:6fec8ced6358b342a21e006fcd53947fbc7baa5ba214539f50b40d6ed603cc94","target":"record","created_at":"2026-07-01T01:18:03Z","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":"9c14278e13c7c08ef24150a4d86643ed90f6f3be8adfd58570a722203ab7f1f2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T10:08:45Z","title_canon_sha256":"1fc464a8bf97eb5267a7e68692ac5ffdabbc43bbff5cedbbd1c699dbfb27a90c"},"schema_version":"1.0","source":{"id":"2606.31435","kind":"arxiv","version":1}},"canonical_sha256":"95a6a592376d71cba033008d3d208ab900f59e6276a13c3a0b223de36024d6fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95a6a592376d71cba033008d3d208ab900f59e6276a13c3a0b223de36024d6fc","first_computed_at":"2026-07-01T01:18:03.152553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:03.152553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9+7ZWZ0PN8gf8UUwJNo8os2/QWO2Y19wpCFlNPWZ83i99RIlPA8NLLCpCIzF/a1qlLl9sOE8VYiPrtiyXk+QDg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:03.152978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31435","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fec8ced6358b342a21e006fcd53947fbc7baa5ba214539f50b40d6ed603cc94","sha256:58f0c1c80ac44a8f1b286bbe54e3cdd84c6ea53d980e85cc120bfcb449d377ff"],"state_sha256":"9e92273dde6f53a31030ee7bb1183d743c63767008ebf003675ae29b3f0ad6f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNmwgHWQcoq/RVQe8E9gnu10TmTT2MrGL8H7WcHAXaocmTqZvcaR/zqZxjiYMZmJ2CJpBVM8+JGWELnph2lPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T17:49:27.791673Z","bundle_sha256":"01fba22c015efb4d0929b742d6715daa3179d254b082837cc9c95168af88fb96"}}