{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MQ3A5LAB6YIO755XZDSVDP7LZC","short_pith_number":"pith:MQ3A5LAB","canonical_record":{"source":{"id":"2605.21180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T13:47:52Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"9ee8257aac07437e1b2704c8cd5ae616fe159766893ecbf93087559abd261ff3","abstract_canon_sha256":"95c7cebe10a85d1df3f0a39d810d06677346bf9a9bdcfc1e7edc10524db5edd2"},"schema_version":"1.0"},"canonical_sha256":"64360eac01f610eff7b7c8e551bfebc8a61bf797bd641e3134c582be3e544df4","source":{"kind":"arxiv","id":"2605.21180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21180","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21180v1","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21180","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"MQ3A5LAB6YIO","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"MQ3A5LAB6YIO755X","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"MQ3A5LAB","created_at":"2026-05-21T01:05:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MQ3A5LAB6YIO755XZDSVDP7LZC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T13:47:52Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"9ee8257aac07437e1b2704c8cd5ae616fe159766893ecbf93087559abd261ff3","abstract_canon_sha256":"95c7cebe10a85d1df3f0a39d810d06677346bf9a9bdcfc1e7edc10524db5edd2"},"schema_version":"1.0"},"canonical_sha256":"64360eac01f610eff7b7c8e551bfebc8a61bf797bd641e3134c582be3e544df4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:41.411744Z","signature_b64":"UVtfFkj835x1v34aQjcJP0zOpl9aUnvIZ98UCwNRcaRaThDnR8zxY2JttrTJtNoiGWoUyyIdTPzyPjtCkKtWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64360eac01f610eff7b7c8e551bfebc8a61bf797bd641e3134c582be3e544df4","last_reissued_at":"2026-05-21T01:05:41.409344Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:41.409344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21180","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":"2026-05-21T01:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tj8nN8XMV2LvvYmBkvStzYojbdB2Szc3bGUxLEAEAgLakdd3H+waU9sSzOnC610vey/tivBvaMd8o0xTHUTJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:16:06.367175Z"},"content_sha256":"57e58a15e7f7bf4070c6d1d5336fd38c8f104035cfe922ce0b6164061f938a19","schema_version":"1.0","event_id":"sha256:57e58a15e7f7bf4070c6d1d5336fd38c8f104035cfe922ce0b6164061f938a19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MQ3A5LAB6YIO755XZDSVDP7LZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Abhinav Anand, Daniel Maninger, Erfan Aghadavoodi Jolfaei, Mert Tiftikci, Mira Mezini","submitted_at":"2026-05-20T13:47:52Z","abstract_excerpt":"Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increasingly being used for planning and executing actions, awareness of the environment and physical constraints is critical. To facilitate the adaption of code-generating LLMs to diverse requirements, including domain-specific ones, we present a reinforcement learning framework that fine-tunes pre-trained LLMs using proximal policy optimization. Our customizable execution-aware rewa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21180","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/2605.21180/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":"2026-05-21T01:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hmbCoc84uZFLbVrlCtuaLcWx/N//JdfQGv7ofNj1KDsbV/Du4MOOoMwnUY/POBj5HFdu0ZwVMC9cqViA87mUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:16:06.367960Z"},"content_sha256":"d8d825ea8f3fc15c6ce26088c44144a6ce92bf77535fd7e8eb8e2efcd220851c","schema_version":"1.0","event_id":"sha256:d8d825ea8f3fc15c6ce26088c44144a6ce92bf77535fd7e8eb8e2efcd220851c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQ3A5LAB6YIO755XZDSVDP7LZC/bundle.json","state_url":"https://pith.science/pith/MQ3A5LAB6YIO755XZDSVDP7LZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQ3A5LAB6YIO755XZDSVDP7LZC/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":"2026-05-26T08:16:06Z","links":{"resolver":"https://pith.science/pith/MQ3A5LAB6YIO755XZDSVDP7LZC","bundle":"https://pith.science/pith/MQ3A5LAB6YIO755XZDSVDP7LZC/bundle.json","state":"https://pith.science/pith/MQ3A5LAB6YIO755XZDSVDP7LZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQ3A5LAB6YIO755XZDSVDP7LZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MQ3A5LAB6YIO755XZDSVDP7LZC","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":"95c7cebe10a85d1df3f0a39d810d06677346bf9a9bdcfc1e7edc10524db5edd2","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T13:47:52Z","title_canon_sha256":"9ee8257aac07437e1b2704c8cd5ae616fe159766893ecbf93087559abd261ff3"},"schema_version":"1.0","source":{"id":"2605.21180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21180","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21180v1","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21180","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"MQ3A5LAB6YIO","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"MQ3A5LAB6YIO755X","created_at":"2026-05-21T01:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"MQ3A5LAB","created_at":"2026-05-21T01:05:41Z"}],"graph_snapshots":[{"event_id":"sha256:d8d825ea8f3fc15c6ce26088c44144a6ce92bf77535fd7e8eb8e2efcd220851c","target":"graph","created_at":"2026-05-21T01:05:41Z","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/2605.21180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increasingly being used for planning and executing actions, awareness of the environment and physical constraints is critical. To facilitate the adaption of code-generating LLMs to diverse requirements, including domain-specific ones, we present a reinforcement learning framework that fine-tunes pre-trained LLMs using proximal policy optimization. Our customizable execution-aware rewa","authors_text":"Abhinav Anand, Daniel Maninger, Erfan Aghadavoodi Jolfaei, Mert Tiftikci, Mira Mezini","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T13:47:52Z","title":"Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21180","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":"sha256:57e58a15e7f7bf4070c6d1d5336fd38c8f104035cfe922ce0b6164061f938a19","target":"record","created_at":"2026-05-21T01:05:41Z","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":"95c7cebe10a85d1df3f0a39d810d06677346bf9a9bdcfc1e7edc10524db5edd2","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T13:47:52Z","title_canon_sha256":"9ee8257aac07437e1b2704c8cd5ae616fe159766893ecbf93087559abd261ff3"},"schema_version":"1.0","source":{"id":"2605.21180","kind":"arxiv","version":1}},"canonical_sha256":"64360eac01f610eff7b7c8e551bfebc8a61bf797bd641e3134c582be3e544df4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64360eac01f610eff7b7c8e551bfebc8a61bf797bd641e3134c582be3e544df4","first_computed_at":"2026-05-21T01:05:41.409344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:41.409344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UVtfFkj835x1v34aQjcJP0zOpl9aUnvIZ98UCwNRcaRaThDnR8zxY2JttrTJtNoiGWoUyyIdTPzyPjtCkKtWCA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:41.411744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57e58a15e7f7bf4070c6d1d5336fd38c8f104035cfe922ce0b6164061f938a19","sha256:d8d825ea8f3fc15c6ce26088c44144a6ce92bf77535fd7e8eb8e2efcd220851c"],"state_sha256":"6e569efa38fd3bdbdd6ddefb5906ee283c1614f0433db20e62a8f786e827a676"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yEUTZC+dASYOWg4zbfgM4Gj2I45HNJjiXBTGGAU83kFYO0caTfsEvj1A1zlQrO6QUxUAjfFe4oRgAABh4upkBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:16:06.371884Z","bundle_sha256":"93bac662ea4180768ab7cc2881be31b2ff3e994cb398679ffb5b7368704591b6"}}