{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JK5D7NGMRO4Q5QY6KY5RVEKJ75","short_pith_number":"pith:JK5D7NGM","canonical_record":{"source":{"id":"2605.29502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:27:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6fdcb3975e3dd2953aea6ede2046e4d1b31eb7c58ac8019163e9a6a1e3e12a1c","abstract_canon_sha256":"2f03e3ff8854d516ab1d2442fcd21e46dffc884d31c7a81bde606f6aaf66c729"},"schema_version":"1.0"},"canonical_sha256":"4aba3fb4cc8bb90ec31e563b1a9149ff673a3a25b6e82f7a1ce4560155c6efc8","source":{"kind":"arxiv","id":"2605.29502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29502","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29502v1","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29502","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"JK5D7NGMRO4Q","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"JK5D7NGMRO4Q5QY6","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"JK5D7NGM","created_at":"2026-05-29T01:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JK5D7NGMRO4Q5QY6KY5RVEKJ75","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:27:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6fdcb3975e3dd2953aea6ede2046e4d1b31eb7c58ac8019163e9a6a1e3e12a1c","abstract_canon_sha256":"2f03e3ff8854d516ab1d2442fcd21e46dffc884d31c7a81bde606f6aaf66c729"},"schema_version":"1.0"},"canonical_sha256":"4aba3fb4cc8bb90ec31e563b1a9149ff673a3a25b6e82f7a1ce4560155c6efc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:43.217019Z","signature_b64":"wZKnL9pnhHqeZhSZXT38k9kzP3OJfeuT4IISPy4pB1YXwNKgXCYxYwBrmuyBTi4ZexUIAEdcxiKDLeO25aIEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aba3fb4cc8bb90ec31e563b1a9149ff673a3a25b6e82f7a1ce4560155c6efc8","last_reissued_at":"2026-05-29T01:05:43.216339Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:43.216339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29502","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":"2026-05-29T01:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mGBX38LRcn7lXRW8eEO8LT/Bfxt/IOjeM5y5gLynqGITk9/eYo+6hFQfOveo19ewl8ABTZwoQrkxznfdUnCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T05:46:13.830651Z"},"content_sha256":"167075393626921ce58c5ad410a78454a4c1fae687ef65d72327d61b3fe3361e","schema_version":"1.0","event_id":"sha256:167075393626921ce58c5ad410a78454a4c1fae687ef65d72327d61b3fe3361e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JK5D7NGMRO4Q5QY6KY5RVEKJ75","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dehan Li, Dingcheng Huang, Jun Zhou, Longfei Zheng, Wentao Zhang, Xiaolu Zhang, Zeli Su, Zewei Pan, Zhankai Xu, Zhou Liu, Ziyin Zhang","submitted_at":"2026-05-28T07:27:16Z","abstract_excerpt":"Low-resource target-language generation is often limited by scarce parallel data, while high-resource source-language monolingual data is abundant but difficult to use with standard supervised fine-tuning. We propose Source-Grounded Semantic Reinforcement Learning (SG-SRL), a resource-utilization framework that converts source-language monolingual data into cross-lingual semantic supervision for target-language generation. SG-SRL performs reference-free reinforcement learning (RL) on source-language data using a cross-lingual semantic reward model, instantiated by a cross-lingual reranker that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29502","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/2605.29502/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":"2026-05-29T01:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"maMP21w6/zX/7r79IQe9XuMjHggXXYhTO/hsijIT2iEeErJRkWVpOV+y6ZwkFKQz6etgWi/V1LYV7hrUhCXAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T05:46:13.831027Z"},"content_sha256":"eda6250acc0168a84c031b3874618ac2a930f7d4780a91a0f6574706cac4fb92","schema_version":"1.0","event_id":"sha256:eda6250acc0168a84c031b3874618ac2a930f7d4780a91a0f6574706cac4fb92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JK5D7NGMRO4Q5QY6KY5RVEKJ75/bundle.json","state_url":"https://pith.science/pith/JK5D7NGMRO4Q5QY6KY5RVEKJ75/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JK5D7NGMRO4Q5QY6KY5RVEKJ75/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":"2026-06-03T05:46:13Z","links":{"resolver":"https://pith.science/pith/JK5D7NGMRO4Q5QY6KY5RVEKJ75","bundle":"https://pith.science/pith/JK5D7NGMRO4Q5QY6KY5RVEKJ75/bundle.json","state":"https://pith.science/pith/JK5D7NGMRO4Q5QY6KY5RVEKJ75/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JK5D7NGMRO4Q5QY6KY5RVEKJ75/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JK5D7NGMRO4Q5QY6KY5RVEKJ75","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":"2f03e3ff8854d516ab1d2442fcd21e46dffc884d31c7a81bde606f6aaf66c729","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:27:16Z","title_canon_sha256":"6fdcb3975e3dd2953aea6ede2046e4d1b31eb7c58ac8019163e9a6a1e3e12a1c"},"schema_version":"1.0","source":{"id":"2605.29502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29502","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29502v1","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29502","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"JK5D7NGMRO4Q","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"JK5D7NGMRO4Q5QY6","created_at":"2026-05-29T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"JK5D7NGM","created_at":"2026-05-29T01:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:eda6250acc0168a84c031b3874618ac2a930f7d4780a91a0f6574706cac4fb92","target":"graph","created_at":"2026-05-29T01:05:43Z","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/2605.29502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-resource target-language generation is often limited by scarce parallel data, while high-resource source-language monolingual data is abundant but difficult to use with standard supervised fine-tuning. We propose Source-Grounded Semantic Reinforcement Learning (SG-SRL), a resource-utilization framework that converts source-language monolingual data into cross-lingual semantic supervision for target-language generation. SG-SRL performs reference-free reinforcement learning (RL) on source-language data using a cross-lingual semantic reward model, instantiated by a cross-lingual reranker that","authors_text":"Dehan Li, Dingcheng Huang, Jun Zhou, Longfei Zheng, Wentao Zhang, Xiaolu Zhang, Zeli Su, Zewei Pan, Zhankai Xu, Zhou Liu, Ziyin Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:27:16Z","title":"Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29502","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":"sha256:167075393626921ce58c5ad410a78454a4c1fae687ef65d72327d61b3fe3361e","target":"record","created_at":"2026-05-29T01:05:43Z","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":"2f03e3ff8854d516ab1d2442fcd21e46dffc884d31c7a81bde606f6aaf66c729","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:27:16Z","title_canon_sha256":"6fdcb3975e3dd2953aea6ede2046e4d1b31eb7c58ac8019163e9a6a1e3e12a1c"},"schema_version":"1.0","source":{"id":"2605.29502","kind":"arxiv","version":1}},"canonical_sha256":"4aba3fb4cc8bb90ec31e563b1a9149ff673a3a25b6e82f7a1ce4560155c6efc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aba3fb4cc8bb90ec31e563b1a9149ff673a3a25b6e82f7a1ce4560155c6efc8","first_computed_at":"2026-05-29T01:05:43.216339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:43.216339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wZKnL9pnhHqeZhSZXT38k9kzP3OJfeuT4IISPy4pB1YXwNKgXCYxYwBrmuyBTi4ZexUIAEdcxiKDLeO25aIEBw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:43.217019Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:167075393626921ce58c5ad410a78454a4c1fae687ef65d72327d61b3fe3361e","sha256:eda6250acc0168a84c031b3874618ac2a930f7d4780a91a0f6574706cac4fb92"],"state_sha256":"5b49e9c9a1d7f52339529828eee75113d25c3b94fdf82695ee71f3b9851404d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGv6HYF2mZ0nng/trNJEN96IymOTQSnPzaK0cG5ihWyEX7IZyU5QdsdgGhZpxwcqUDbhC96QZYX677BssPOWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T05:46:13.833260Z","bundle_sha256":"8d1f479a9b65b86ace5c541bd5edc021c771e7a5d73e8ac1b9dcd25c210d60a3"}}