{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NMZKXXJA4ETFKMLXZVISLAINPV","short_pith_number":"pith:NMZKXXJA","canonical_record":{"source":{"id":"2506.00103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"ed9f30c73101513a732496c72701503e49f83c0d34b0371a543bb8dfe0b1deae","abstract_canon_sha256":"540512b6eaa919153c6df55380bd28d5e916310ffff8c2fd77489c7040dc5a9c"},"schema_version":"1.0"},"canonical_sha256":"6b32abdd20e126553177cd5125810d7d5275842f2bfa32a47bf22a66b865c3ef","source":{"kind":"arxiv","id":"2506.00103","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00103","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00103v2","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00103","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"NMZKXXJA4ETF","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"NMZKXXJA4ETFKMLX","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"NMZKXXJA","created_at":"2026-07-05T11:19:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NMZKXXJA4ETFKMLXZVISLAINPV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"ed9f30c73101513a732496c72701503e49f83c0d34b0371a543bb8dfe0b1deae","abstract_canon_sha256":"540512b6eaa919153c6df55380bd28d5e916310ffff8c2fd77489c7040dc5a9c"},"schema_version":"1.0"},"canonical_sha256":"6b32abdd20e126553177cd5125810d7d5275842f2bfa32a47bf22a66b865c3ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:53.168536Z","signature_b64":"D4b6Aa22Nln5Tot4SZymGq6+0YgFG1CC6dP7H/K0VYFPT2ZLqae2DafVw0zOiIrp7YlwiaCaXD0Vv2GtYhzGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b32abdd20e126553177cd5125810d7d5275842f2bfa32a47bf22a66b865c3ef","last_reissued_at":"2026-07-05T11:19:53.168112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:53.168112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00103","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":"2026-07-05T11:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9mJHGXSSsZcPpxdeyBFMuthgqsIkL8gYbYgoHLeyTmy7P4bEJitBKHxUEpS0Bz+ozas39G1QzcQgIRR20xZBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T08:22:41.199988Z"},"content_sha256":"e86044cbc737770fec978b344560e02a1fd9464df15bf9c793c29489f20d1577","schema_version":"1.0","event_id":"sha256:e86044cbc737770fec978b344560e02a1fd9464df15bf9c793c29489f20d1577"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NMZKXXJA4ETFKMLXZVISLAINPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanjun Jiang, Jianhe Lin, Kai Luo, Ruipeng Jia, Shihao Huang, Xiaoxi Jiang, Yongbo Gai, Yunyi Yang","submitted_at":"2025-05-30T14:34:57Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has enabled large language models (LLMs) to achieve remarkable breakthroughs in reasoning tasks with objective ground-truth answers, such as mathematics and code generation. However, a significant gap remains for non-verifiable tasks, like creative writing and open-ended dialogue, where quality assessment is inherently subjective and lacks definitive references. Existing approaches for these domains often rely on scalar reward models trained with human preferences, which suffer from limited generalization and are prone to reward hacking, su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00103","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/2506.00103/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":"2026-07-05T11:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EgndgZCtn7SzCr2OpjZ31VSbHIV3CPZmHuKaA4sqo55ugAVVPzMCB0tDGDjOcBcxZNym8ffuim8oZ1Q1p0M0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T08:22:41.200507Z"},"content_sha256":"fefe66926ffaea9aac138a0e08b563b1ef6bee95449d3bc8f5f1a3a10baea665","schema_version":"1.0","event_id":"sha256:fefe66926ffaea9aac138a0e08b563b1ef6bee95449d3bc8f5f1a3a10baea665"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMZKXXJA4ETFKMLXZVISLAINPV/bundle.json","state_url":"https://pith.science/pith/NMZKXXJA4ETFKMLXZVISLAINPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMZKXXJA4ETFKMLXZVISLAINPV/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":"2026-08-03T08:22:41Z","links":{"resolver":"https://pith.science/pith/NMZKXXJA4ETFKMLXZVISLAINPV","bundle":"https://pith.science/pith/NMZKXXJA4ETFKMLXZVISLAINPV/bundle.json","state":"https://pith.science/pith/NMZKXXJA4ETFKMLXZVISLAINPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMZKXXJA4ETFKMLXZVISLAINPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NMZKXXJA4ETFKMLXZVISLAINPV","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":"540512b6eaa919153c6df55380bd28d5e916310ffff8c2fd77489c7040dc5a9c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:34:57Z","title_canon_sha256":"ed9f30c73101513a732496c72701503e49f83c0d34b0371a543bb8dfe0b1deae"},"schema_version":"1.0","source":{"id":"2506.00103","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00103","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00103v2","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00103","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"NMZKXXJA4ETF","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"NMZKXXJA4ETFKMLX","created_at":"2026-07-05T11:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"NMZKXXJA","created_at":"2026-07-05T11:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:fefe66926ffaea9aac138a0e08b563b1ef6bee95449d3bc8f5f1a3a10baea665","target":"graph","created_at":"2026-07-05T11:19:53Z","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/2506.00103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has enabled large language models (LLMs) to achieve remarkable breakthroughs in reasoning tasks with objective ground-truth answers, such as mathematics and code generation. However, a significant gap remains for non-verifiable tasks, like creative writing and open-ended dialogue, where quality assessment is inherently subjective and lacks definitive references. Existing approaches for these domains often rely on scalar reward models trained with human preferences, which suffer from limited generalization and are prone to reward hacking, su","authors_text":"Guanjun Jiang, Jianhe Lin, Kai Luo, Ruipeng Jia, Shihao Huang, Xiaoxi Jiang, Yongbo Gai, Yunyi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:34:57Z","title":"Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00103","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:e86044cbc737770fec978b344560e02a1fd9464df15bf9c793c29489f20d1577","target":"record","created_at":"2026-07-05T11:19:53Z","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":"540512b6eaa919153c6df55380bd28d5e916310ffff8c2fd77489c7040dc5a9c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:34:57Z","title_canon_sha256":"ed9f30c73101513a732496c72701503e49f83c0d34b0371a543bb8dfe0b1deae"},"schema_version":"1.0","source":{"id":"2506.00103","kind":"arxiv","version":2}},"canonical_sha256":"6b32abdd20e126553177cd5125810d7d5275842f2bfa32a47bf22a66b865c3ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b32abdd20e126553177cd5125810d7d5275842f2bfa32a47bf22a66b865c3ef","first_computed_at":"2026-07-05T11:19:53.168112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:53.168112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D4b6Aa22Nln5Tot4SZymGq6+0YgFG1CC6dP7H/K0VYFPT2ZLqae2DafVw0zOiIrp7YlwiaCaXD0Vv2GtYhzGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:53.168536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00103","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e86044cbc737770fec978b344560e02a1fd9464df15bf9c793c29489f20d1577","sha256:fefe66926ffaea9aac138a0e08b563b1ef6bee95449d3bc8f5f1a3a10baea665"],"state_sha256":"d0d89f21a4b3576847be9809ec9ed98eabc2c8712da46c947bb0223aab57a4ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MO9nUFzNr+B3SVdRuuk3SVAtY5RZ9lyRt8cKedIqg63toCmw8vAKmm6KzXA7KV1cltngNpWeMLZ2Dkfi5KICCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T08:22:41.205813Z","bundle_sha256":"b4a43d57d9664a670e10371c2e8c906b17d8f03fe8d2bd38ab2357539f2dadd0"}}