{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H6F3GTQGK4EYNZPYHDCPG4436J","short_pith_number":"pith:H6F3GTQG","canonical_record":{"source":{"id":"2512.03086","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-11-29T05:26:53Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"664a3a63e7c4f7b7f40d8c43a3b2ae728535d0ddb81ac13cf90c10a6e5629772","abstract_canon_sha256":"93ddd66aee533efad97d34d9df9e0d86328519a8db77293f90d55555afc82dc2"},"schema_version":"1.0"},"canonical_sha256":"3f8bb34e06570986e5f838c4f3739bf261dc4a677833ac14713a9d90d8b7d168","source":{"kind":"arxiv","id":"2512.03086","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.03086","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2512.03086v2","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.03086","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"H6F3GTQGK4EY","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"H6F3GTQGK4EYNZPY","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"H6F3GTQG","created_at":"2026-06-05T00:13:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H6F3GTQGK4EYNZPYHDCPG4436J","target":"record","payload":{"canonical_record":{"source":{"id":"2512.03086","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-11-29T05:26:53Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"664a3a63e7c4f7b7f40d8c43a3b2ae728535d0ddb81ac13cf90c10a6e5629772","abstract_canon_sha256":"93ddd66aee533efad97d34d9df9e0d86328519a8db77293f90d55555afc82dc2"},"schema_version":"1.0"},"canonical_sha256":"3f8bb34e06570986e5f838c4f3739bf261dc4a677833ac14713a9d90d8b7d168","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:44.572230Z","signature_b64":"EV85erv8VL9dQU/uFWt+h3+DjaiMy9W6WZOmn1Ty2EOGc0aFFtCDCMLADIgNNki9QbzRMng63jgGi/4GqmO7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8bb34e06570986e5f838c4f3739bf261dc4a677833ac14713a9d90d8b7d168","last_reissued_at":"2026-06-05T00:13:44.571718Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:44.571718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.03086","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":"2026-06-05T00:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQibjinBKG3pmP0bfcTPOja4wvjnuIOMk0w1UI4glfF/V0VXhOTwpEZP3lY9lOQpq3iBm474z3N8rOyGFJU5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:28:11.348849Z"},"content_sha256":"08aa675f9042a767f6c7718a14f13a37c2725688ca07b9a5d4bf57234fd79290","schema_version":"1.0","event_id":"sha256:08aa675f9042a767f6c7718a14f13a37c2725688ca07b9a5d4bf57234fd79290"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H6F3GTQGK4EYNZPYHDCPG4436J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.PL","authors_text":"Ali Jannesari, Bin Lei, Caiwen Ding, Chunhua Liao, Dunzhi Zhou, Le Chen, Nuo Xu, Pei-Hung Lin, Rajeev Thakur, Winson Chen","submitted_at":"2025-11-29T05:26:53Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA, where high-quality parallel data are scarce. We present an automated dataset generation pipeline featuring a dual-LLM Questioner-Solver design that incorporates external knowledge from compilers and runtime feedback. Beyond traditional source-target code pair datasets, our approach additionally generates (1) verified translations with unit tests for assessing functional consistency and (2) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.03086","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/2512.03086/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":"2026-06-05T00:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WesJntgK4y5mWdYeMyT+PalvpYo1q8ctfhZvBAmjJhJ7fFfmMwUt5oOXwMZCCMYk2TjbAOL5KXs0xvq43xsvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:28:11.349214Z"},"content_sha256":"2fbdbed71d1b31d5d9a51254d81a9d1a43bdd89b3cafadfcaa7d46d5c3c3157e","schema_version":"1.0","event_id":"sha256:2fbdbed71d1b31d5d9a51254d81a9d1a43bdd89b3cafadfcaa7d46d5c3c3157e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/bundle.json","state_url":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6F3GTQGK4EYNZPYHDCPG4436J/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":"2026-06-28T15:28:11Z","links":{"resolver":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J","bundle":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/bundle.json","state":"https://pith.science/pith/H6F3GTQGK4EYNZPYHDCPG4436J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6F3GTQGK4EYNZPYHDCPG4436J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H6F3GTQGK4EYNZPYHDCPG4436J","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":"93ddd66aee533efad97d34d9df9e0d86328519a8db77293f90d55555afc82dc2","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-11-29T05:26:53Z","title_canon_sha256":"664a3a63e7c4f7b7f40d8c43a3b2ae728535d0ddb81ac13cf90c10a6e5629772"},"schema_version":"1.0","source":{"id":"2512.03086","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.03086","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2512.03086v2","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.03086","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"H6F3GTQGK4EY","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"H6F3GTQGK4EYNZPY","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"H6F3GTQG","created_at":"2026-06-05T00:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:2fbdbed71d1b31d5d9a51254d81a9d1a43bdd89b3cafadfcaa7d46d5c3c3157e","target":"graph","created_at":"2026-06-05T00:13:44Z","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/2512.03086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA, where high-quality parallel data are scarce. We present an automated dataset generation pipeline featuring a dual-LLM Questioner-Solver design that incorporates external knowledge from compilers and runtime feedback. Beyond traditional source-target code pair datasets, our approach additionally generates (1) verified translations with unit tests for assessing functional consistency and (2) ","authors_text":"Ali Jannesari, Bin Lei, Caiwen Ding, Chunhua Liao, Dunzhi Zhou, Le Chen, Nuo Xu, Pei-Hung Lin, Rajeev Thakur, Winson Chen","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-11-29T05:26:53Z","title":"Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.03086","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":"sha256:08aa675f9042a767f6c7718a14f13a37c2725688ca07b9a5d4bf57234fd79290","target":"record","created_at":"2026-06-05T00:13:44Z","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":"93ddd66aee533efad97d34d9df9e0d86328519a8db77293f90d55555afc82dc2","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-11-29T05:26:53Z","title_canon_sha256":"664a3a63e7c4f7b7f40d8c43a3b2ae728535d0ddb81ac13cf90c10a6e5629772"},"schema_version":"1.0","source":{"id":"2512.03086","kind":"arxiv","version":2}},"canonical_sha256":"3f8bb34e06570986e5f838c4f3739bf261dc4a677833ac14713a9d90d8b7d168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f8bb34e06570986e5f838c4f3739bf261dc4a677833ac14713a9d90d8b7d168","first_computed_at":"2026-06-05T00:13:44.571718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:44.571718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EV85erv8VL9dQU/uFWt+h3+DjaiMy9W6WZOmn1Ty2EOGc0aFFtCDCMLADIgNNki9QbzRMng63jgGi/4GqmO7Aw==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:44.572230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.03086","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08aa675f9042a767f6c7718a14f13a37c2725688ca07b9a5d4bf57234fd79290","sha256:2fbdbed71d1b31d5d9a51254d81a9d1a43bdd89b3cafadfcaa7d46d5c3c3157e"],"state_sha256":"1f0c3b6b9287a7d0235d2050876e15dbec2932c0bd76afd579464d3621512f54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cq8kISuHhKXD7/AgonVFZV0gKDP//+U/qba1q/7Zpcn5ZcVUHDyOtwEC8UoYQDyBdxRa/mFmIanqyVfNS1yEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T15:28:11.351202Z","bundle_sha256":"79fa26165d1e603fd9ba715c1829f462f9ea0319c5794c20a6026f1a35c5317b"}}