{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W4UO4CJZI6HA3YJ7B3M4PNHM5V","short_pith_number":"pith:W4UO4CJZ","canonical_record":{"source":{"id":"2409.19715","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T14:14:25Z","cross_cats_sorted":[],"title_canon_sha256":"fbf30f9c60a7a97a5c1dd72835fbbdd172388fc59e45ad2a134db6fa0df9c86c","abstract_canon_sha256":"809787940014f4c32798a45e0ef8e95b75e9c99f7f53876a4d44f0b28cc06ae6"},"schema_version":"1.0"},"canonical_sha256":"b728ee0939478e0de13f0ed9c7b4eced6117a166a3bf07cbcb1c362780079d9b","source":{"kind":"arxiv","id":"2409.19715","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19715","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19715v2","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19715","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"W4UO4CJZI6HA","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"W4UO4CJZI6HA3YJ7","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"W4UO4CJZ","created_at":"2026-07-05T09:15:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W4UO4CJZI6HA3YJ7B3M4PNHM5V","target":"record","payload":{"canonical_record":{"source":{"id":"2409.19715","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T14:14:25Z","cross_cats_sorted":[],"title_canon_sha256":"fbf30f9c60a7a97a5c1dd72835fbbdd172388fc59e45ad2a134db6fa0df9c86c","abstract_canon_sha256":"809787940014f4c32798a45e0ef8e95b75e9c99f7f53876a4d44f0b28cc06ae6"},"schema_version":"1.0"},"canonical_sha256":"b728ee0939478e0de13f0ed9c7b4eced6117a166a3bf07cbcb1c362780079d9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:38.279243Z","signature_b64":"+uQVslCFRJ9fPaJDtPkRQdt2D5mohLO94T4u53a872yteIcomGWtBqIuxfuuHK+zRlEMS0+kgf5w8ffpiMgxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b728ee0939478e0de13f0ed9c7b4eced6117a166a3bf07cbcb1c362780079d9b","last_reissued_at":"2026-07-05T09:15:38.278767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:38.278767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.19715","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":"2026-07-05T09:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ftH8qzA7StQgh8bBJI8CPAZCGmsl3nRxc4wdw9HVLpmKH5fXAYLG3hItKsjAwEeGdCsUdnl4qn4nxU1/NJHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:27:02.473452Z"},"content_sha256":"3b0bf26c8c84fca673cb44849482990d9f74c76b3d203c7b3f940f92d6c9063d","schema_version":"1.0","event_id":"sha256:3b0bf26c8c84fca673cb44849482990d9f74c76b3d203c7b3f940f92d6c9063d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W4UO4CJZI6HA3YJ7B3M4PNHM5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beong-woo Kwak, Dongjin Kang, Hyungjoo Chae, Jinyoung Yeo, Kai Tzu-iunn Ong, Seonghyeon Bae, Seungjun Moon, Seung-won Hwang, Taeyoon Kwon, Yongho Song","submitted_at":"2024-09-29T14:14:25Z","abstract_excerpt":"This paper presents Coffee-Gym, a comprehensive RL environment for training models that provide feedback on code editing. Coffee-Gym includes two major components: (1) Coffee, a dataset containing humans' code edit traces for coding questions and machine-written feedback for editing erroneous code; (2) CoffeeEval, a reward function that faithfully reflects the helpfulness of feedback by assessing the performance of the revised code in unit tests. With them, Coffee-Gym addresses the unavailability of high-quality datasets for training feedback models with RL, and provides more accurate rewards "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19715","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/2409.19715/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":"2026-07-05T09:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QREzEjYzAVFe1M9RVCZ0kQkWwn756KG+AXSxiMFTmyDIdsZ0Y3gV+D78Gb2qA4mDpmRD/4Y8ylHoioBeEwp8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:27:02.473997Z"},"content_sha256":"3e85769cfdbe70e3202e27fa2691c2dfc7b4d5ff7e18bfa2bf95ef6db0432a84","schema_version":"1.0","event_id":"sha256:3e85769cfdbe70e3202e27fa2691c2dfc7b4d5ff7e18bfa2bf95ef6db0432a84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4UO4CJZI6HA3YJ7B3M4PNHM5V/bundle.json","state_url":"https://pith.science/pith/W4UO4CJZI6HA3YJ7B3M4PNHM5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4UO4CJZI6HA3YJ7B3M4PNHM5V/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":"2026-08-10T14:27:02Z","links":{"resolver":"https://pith.science/pith/W4UO4CJZI6HA3YJ7B3M4PNHM5V","bundle":"https://pith.science/pith/W4UO4CJZI6HA3YJ7B3M4PNHM5V/bundle.json","state":"https://pith.science/pith/W4UO4CJZI6HA3YJ7B3M4PNHM5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4UO4CJZI6HA3YJ7B3M4PNHM5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W4UO4CJZI6HA3YJ7B3M4PNHM5V","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":"809787940014f4c32798a45e0ef8e95b75e9c99f7f53876a4d44f0b28cc06ae6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T14:14:25Z","title_canon_sha256":"fbf30f9c60a7a97a5c1dd72835fbbdd172388fc59e45ad2a134db6fa0df9c86c"},"schema_version":"1.0","source":{"id":"2409.19715","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19715","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19715v2","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19715","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"W4UO4CJZI6HA","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"W4UO4CJZI6HA3YJ7","created_at":"2026-07-05T09:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"W4UO4CJZ","created_at":"2026-07-05T09:15:38Z"}],"graph_snapshots":[{"event_id":"sha256:3e85769cfdbe70e3202e27fa2691c2dfc7b4d5ff7e18bfa2bf95ef6db0432a84","target":"graph","created_at":"2026-07-05T09:15:38Z","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/2409.19715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents Coffee-Gym, a comprehensive RL environment for training models that provide feedback on code editing. Coffee-Gym includes two major components: (1) Coffee, a dataset containing humans' code edit traces for coding questions and machine-written feedback for editing erroneous code; (2) CoffeeEval, a reward function that faithfully reflects the helpfulness of feedback by assessing the performance of the revised code in unit tests. With them, Coffee-Gym addresses the unavailability of high-quality datasets for training feedback models with RL, and provides more accurate rewards ","authors_text":"Beong-woo Kwak, Dongjin Kang, Hyungjoo Chae, Jinyoung Yeo, Kai Tzu-iunn Ong, Seonghyeon Bae, Seungjun Moon, Seung-won Hwang, Taeyoon Kwon, Yongho Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T14:14:25Z","title":"Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19715","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":"sha256:3b0bf26c8c84fca673cb44849482990d9f74c76b3d203c7b3f940f92d6c9063d","target":"record","created_at":"2026-07-05T09:15:38Z","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":"809787940014f4c32798a45e0ef8e95b75e9c99f7f53876a4d44f0b28cc06ae6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T14:14:25Z","title_canon_sha256":"fbf30f9c60a7a97a5c1dd72835fbbdd172388fc59e45ad2a134db6fa0df9c86c"},"schema_version":"1.0","source":{"id":"2409.19715","kind":"arxiv","version":2}},"canonical_sha256":"b728ee0939478e0de13f0ed9c7b4eced6117a166a3bf07cbcb1c362780079d9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b728ee0939478e0de13f0ed9c7b4eced6117a166a3bf07cbcb1c362780079d9b","first_computed_at":"2026-07-05T09:15:38.278767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:38.278767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+uQVslCFRJ9fPaJDtPkRQdt2D5mohLO94T4u53a872yteIcomGWtBqIuxfuuHK+zRlEMS0+kgf5w8ffpiMgxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:38.279243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19715","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b0bf26c8c84fca673cb44849482990d9f74c76b3d203c7b3f940f92d6c9063d","sha256:3e85769cfdbe70e3202e27fa2691c2dfc7b4d5ff7e18bfa2bf95ef6db0432a84"],"state_sha256":"a7dc864961233f15bf2aefdef7e4a6da617a406fca4219aaf68bfcdeb98fdb9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z/olQJtsSCPHXLtBqyd4HeCx7uQ4ndyWpBJpGFlzkzAvCInoqlHRxMQI/wNSH6+pSemsgZsGjGe+YokjcXEuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:27:02.478657Z","bundle_sha256":"84c08165cd5432dd27be948c8d2ca0fe048c523892f626abb9e3f5dd99f64555"}}