{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:V325N4CRRLIT5APD3CBBVITJG7","short_pith_number":"pith:V325N4CR","canonical_record":{"source":{"id":"2207.01780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T02:42:15Z","cross_cats_sorted":["cs.CL","cs.PL"],"title_canon_sha256":"a80c9aeb8cf3af35533f573adcb781e09f10cb093234b239e9648f6fe2fffdbf","abstract_canon_sha256":"627310f584db4f7fcc3101dad68a69b184ba4d2a28d1fc0e8b6ec140be0a15e2"},"schema_version":"1.0"},"canonical_sha256":"aef5d6f0518ad13e81e3d8821aa26937e174a913ea3c3173c7be1fa9fc5384c0","source":{"kind":"arxiv","id":"2207.01780","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.01780","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"arxiv_version","alias_value":"2207.01780v3","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01780","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"pith_short_12","alias_value":"V325N4CRRLIT","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"pith_short_16","alias_value":"V325N4CRRLIT5APD","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"pith_short_8","alias_value":"V325N4CR","created_at":"2026-07-05T05:12:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:V325N4CRRLIT5APD3CBBVITJG7","target":"record","payload":{"canonical_record":{"source":{"id":"2207.01780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T02:42:15Z","cross_cats_sorted":["cs.CL","cs.PL"],"title_canon_sha256":"a80c9aeb8cf3af35533f573adcb781e09f10cb093234b239e9648f6fe2fffdbf","abstract_canon_sha256":"627310f584db4f7fcc3101dad68a69b184ba4d2a28d1fc0e8b6ec140be0a15e2"},"schema_version":"1.0"},"canonical_sha256":"aef5d6f0518ad13e81e3d8821aa26937e174a913ea3c3173c7be1fa9fc5384c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:52.214261Z","signature_b64":"2P1NPsb9o62Q1D7Tg4O48fQ7pvFWFKQ4HKmaO2rtrF/Eae/6Wo6UkTM9JOKTiKsEOWJKAJBuRDiam9AuR9lODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aef5d6f0518ad13e81e3d8821aa26937e174a913ea3c3173c7be1fa9fc5384c0","last_reissued_at":"2026-07-05T05:12:52.213784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:52.213784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.01780","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":"2026-07-05T05:12:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uej6RaxyA99sp4XwBlQG/45fOQOTxPYeiwPyKz0XqBBwHO9oUZPzgal7mzKiT16fxYJav2CgyevwJXmksvWwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:53:24.522412Z"},"content_sha256":"428187b3adf93d84b744cea5e1a2632377ab5eb1c09c708e7da9077d119a2eaf","schema_version":"1.0","event_id":"sha256:428187b3adf93d84b744cea5e1a2632377ab5eb1c09c708e7da9077d119a2eaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:V325N4CRRLIT5APD3CBBVITJG7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.PL"],"primary_cat":"cs.LG","authors_text":"Akhilesh Deepak Gotmare, Hung Le, Silvio Savarese, Steven C.H. Hoi, Yue Wang","submitted_at":"2022-07-05T02:42:15Z","abstract_excerpt":"Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01780","kind":"arxiv","version":3},"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/2207.01780/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":"2026-07-05T05:12:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xDjQkOmYm0hPTR8RH8fdmJWsNUfjQktLAlXwlou4CGbpHvQ5qX9jZBOZa2LbxbcdpAYQkLhqffvlBJok++YDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:53:24.522931Z"},"content_sha256":"7390f36694799165ff0ac8ae1a95c07f18f910c44a003e7f07dfa4ae7763d700","schema_version":"1.0","event_id":"sha256:7390f36694799165ff0ac8ae1a95c07f18f910c44a003e7f07dfa4ae7763d700"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V325N4CRRLIT5APD3CBBVITJG7/bundle.json","state_url":"https://pith.science/pith/V325N4CRRLIT5APD3CBBVITJG7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V325N4CRRLIT5APD3CBBVITJG7/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":"2026-08-06T05:53:24Z","links":{"resolver":"https://pith.science/pith/V325N4CRRLIT5APD3CBBVITJG7","bundle":"https://pith.science/pith/V325N4CRRLIT5APD3CBBVITJG7/bundle.json","state":"https://pith.science/pith/V325N4CRRLIT5APD3CBBVITJG7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V325N4CRRLIT5APD3CBBVITJG7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V325N4CRRLIT5APD3CBBVITJG7","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":"627310f584db4f7fcc3101dad68a69b184ba4d2a28d1fc0e8b6ec140be0a15e2","cross_cats_sorted":["cs.CL","cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T02:42:15Z","title_canon_sha256":"a80c9aeb8cf3af35533f573adcb781e09f10cb093234b239e9648f6fe2fffdbf"},"schema_version":"1.0","source":{"id":"2207.01780","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.01780","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"arxiv_version","alias_value":"2207.01780v3","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01780","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"pith_short_12","alias_value":"V325N4CRRLIT","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"pith_short_16","alias_value":"V325N4CRRLIT5APD","created_at":"2026-07-05T05:12:52Z"},{"alias_kind":"pith_short_8","alias_value":"V325N4CR","created_at":"2026-07-05T05:12:52Z"}],"graph_snapshots":[{"event_id":"sha256:7390f36694799165ff0ac8ae1a95c07f18f910c44a003e7f07dfa4ae7763d700","target":"graph","created_at":"2026-07-05T05:12:52Z","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/2207.01780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor ","authors_text":"Akhilesh Deepak Gotmare, Hung Le, Silvio Savarese, Steven C.H. Hoi, Yue Wang","cross_cats":["cs.CL","cs.PL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T02:42:15Z","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01780","kind":"arxiv","version":3},"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":"sha256:428187b3adf93d84b744cea5e1a2632377ab5eb1c09c708e7da9077d119a2eaf","target":"record","created_at":"2026-07-05T05:12:52Z","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":"627310f584db4f7fcc3101dad68a69b184ba4d2a28d1fc0e8b6ec140be0a15e2","cross_cats_sorted":["cs.CL","cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T02:42:15Z","title_canon_sha256":"a80c9aeb8cf3af35533f573adcb781e09f10cb093234b239e9648f6fe2fffdbf"},"schema_version":"1.0","source":{"id":"2207.01780","kind":"arxiv","version":3}},"canonical_sha256":"aef5d6f0518ad13e81e3d8821aa26937e174a913ea3c3173c7be1fa9fc5384c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aef5d6f0518ad13e81e3d8821aa26937e174a913ea3c3173c7be1fa9fc5384c0","first_computed_at":"2026-07-05T05:12:52.213784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:52.213784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2P1NPsb9o62Q1D7Tg4O48fQ7pvFWFKQ4HKmaO2rtrF/Eae/6Wo6UkTM9JOKTiKsEOWJKAJBuRDiam9AuR9lODA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:52.214261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.01780","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:428187b3adf93d84b744cea5e1a2632377ab5eb1c09c708e7da9077d119a2eaf","sha256:7390f36694799165ff0ac8ae1a95c07f18f910c44a003e7f07dfa4ae7763d700"],"state_sha256":"27d1848dc947cdc6d2b47e6b6ba3c760cc76ba89808d31fd00f00f2a6a443e31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1PXTFxbBXdZ89nrTN1ad5u1LsAYfJoNG+gSFX/iGazEeTvS/RIFlKxL01NH0U9kfPS9l5VnX9xCsZOPmhgaPDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:53:24.527966Z","bundle_sha256":"8a3ea9fc672dba8f61be886949dde30bfb914f3d7692df85b79e0f8b0b97415f"}}