{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CUMTZLPDYJSPZ2KA3RNR2MKCMO","short_pith_number":"pith:CUMTZLPD","canonical_record":{"source":{"id":"2505.13988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:36:45Z","cross_cats_sorted":[],"title_canon_sha256":"bf2be439dfcdaa0467c07dd383749a349971bf427c7fcb11e3f0b5adb6fff762","abstract_canon_sha256":"8a7b2c19cd1faea19eb8d0c12bdd7f7ad6ef0a3a26808835d040eb55c39d188c"},"schema_version":"1.0"},"canonical_sha256":"15193cade3c264fce940dc5b1d3142638807ec413e4da723d8734684ca18716f","source":{"kind":"arxiv","id":"2505.13988","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13988","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13988v1","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13988","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"CUMTZLPDYJSP","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"CUMTZLPDYJSPZ2KA","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"CUMTZLPD","created_at":"2026-07-05T11:05:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CUMTZLPDYJSPZ2KA3RNR2MKCMO","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:36:45Z","cross_cats_sorted":[],"title_canon_sha256":"bf2be439dfcdaa0467c07dd383749a349971bf427c7fcb11e3f0b5adb6fff762","abstract_canon_sha256":"8a7b2c19cd1faea19eb8d0c12bdd7f7ad6ef0a3a26808835d040eb55c39d188c"},"schema_version":"1.0"},"canonical_sha256":"15193cade3c264fce940dc5b1d3142638807ec413e4da723d8734684ca18716f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:54.327883Z","signature_b64":"lS9nf6qFVX4JYMojZkq6FrPYX8JjoGK9VlVBIFRwqZTq8rPNrwcFHQtkzQtgZnDMnqtUQtEjbFSYK47ysC7TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15193cade3c264fce940dc5b1d3142638807ec413e4da723d8734684ca18716f","last_reissued_at":"2026-07-05T11:05:54.327449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:54.327449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13988","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":"2026-07-05T11:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzC9DXsd9MTZsnVTB2vECgJw9j7x1A8y7kbqQuVcAElnRYSOj43ApjpfWy+4FTd2cTJPHElWu0IxYHayQOeMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:25:24.746719Z"},"content_sha256":"4ed731b0b56b0ff0fda3cfcf2c466917eb4d76d5e41018dec087fb43c8d750cd","schema_version":"1.0","event_id":"sha256:4ed731b0b56b0ff0fda3cfcf2c466917eb4d76d5e41018dec087fb43c8d750cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CUMTZLPDYJSPZ2KA3RNR2MKCMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Hallucination Tax of Reinforcement Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jieyu Zhao, Linxin Song, Taiwei Shi","submitted_at":"2025-05-20T06:36:45Z","abstract_excerpt":"Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). However, its impact on model trustworthiness remains underexplored. In this work, we identify and systematically study a critical side effect of RFT, which we term the hallucination tax: a degradation in refusal behavior causing models to produce hallucinated answers to unanswerable questions confidently. To investigate this, we introduce SUM (Synthetic Unanswerable Math), a high-quality dataset of unanswerable math problems designed to probe models' ability t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13988","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/2505.13988/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":"2026-07-05T11:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1VRrsPmtdVeeaDKj22nvrtqqDcq/U72zi9hEj4qFDn2KGydJ2fejHpbCHtsC6dqtxXCTVmbHfiDq9kylDvXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:25:24.747235Z"},"content_sha256":"e60c6aba3258ae61f5707347aa72a8abcb44ab23b28df50e1e9a9eb96f81e995","schema_version":"1.0","event_id":"sha256:e60c6aba3258ae61f5707347aa72a8abcb44ab23b28df50e1e9a9eb96f81e995"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUMTZLPDYJSPZ2KA3RNR2MKCMO/bundle.json","state_url":"https://pith.science/pith/CUMTZLPDYJSPZ2KA3RNR2MKCMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUMTZLPDYJSPZ2KA3RNR2MKCMO/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":"2026-08-07T21:25:24Z","links":{"resolver":"https://pith.science/pith/CUMTZLPDYJSPZ2KA3RNR2MKCMO","bundle":"https://pith.science/pith/CUMTZLPDYJSPZ2KA3RNR2MKCMO/bundle.json","state":"https://pith.science/pith/CUMTZLPDYJSPZ2KA3RNR2MKCMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUMTZLPDYJSPZ2KA3RNR2MKCMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CUMTZLPDYJSPZ2KA3RNR2MKCMO","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":"8a7b2c19cd1faea19eb8d0c12bdd7f7ad6ef0a3a26808835d040eb55c39d188c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:36:45Z","title_canon_sha256":"bf2be439dfcdaa0467c07dd383749a349971bf427c7fcb11e3f0b5adb6fff762"},"schema_version":"1.0","source":{"id":"2505.13988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13988","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13988v1","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13988","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"CUMTZLPDYJSP","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"CUMTZLPDYJSPZ2KA","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"CUMTZLPD","created_at":"2026-07-05T11:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:e60c6aba3258ae61f5707347aa72a8abcb44ab23b28df50e1e9a9eb96f81e995","target":"graph","created_at":"2026-07-05T11:05:54Z","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/2505.13988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). However, its impact on model trustworthiness remains underexplored. In this work, we identify and systematically study a critical side effect of RFT, which we term the hallucination tax: a degradation in refusal behavior causing models to produce hallucinated answers to unanswerable questions confidently. To investigate this, we introduce SUM (Synthetic Unanswerable Math), a high-quality dataset of unanswerable math problems designed to probe models' ability t","authors_text":"Jieyu Zhao, Linxin Song, Taiwei Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:36:45Z","title":"The Hallucination Tax of Reinforcement Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13988","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":"sha256:4ed731b0b56b0ff0fda3cfcf2c466917eb4d76d5e41018dec087fb43c8d750cd","target":"record","created_at":"2026-07-05T11:05:54Z","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":"8a7b2c19cd1faea19eb8d0c12bdd7f7ad6ef0a3a26808835d040eb55c39d188c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:36:45Z","title_canon_sha256":"bf2be439dfcdaa0467c07dd383749a349971bf427c7fcb11e3f0b5adb6fff762"},"schema_version":"1.0","source":{"id":"2505.13988","kind":"arxiv","version":1}},"canonical_sha256":"15193cade3c264fce940dc5b1d3142638807ec413e4da723d8734684ca18716f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15193cade3c264fce940dc5b1d3142638807ec413e4da723d8734684ca18716f","first_computed_at":"2026-07-05T11:05:54.327449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:54.327449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lS9nf6qFVX4JYMojZkq6FrPYX8JjoGK9VlVBIFRwqZTq8rPNrwcFHQtkzQtgZnDMnqtUQtEjbFSYK47ysC7TCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:54.327883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ed731b0b56b0ff0fda3cfcf2c466917eb4d76d5e41018dec087fb43c8d750cd","sha256:e60c6aba3258ae61f5707347aa72a8abcb44ab23b28df50e1e9a9eb96f81e995"],"state_sha256":"a03759e57c2872253f89f6258931c76a9d9d2057b7f9cf46065ed7e9612dba0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RC6cNOxuRoZ+AhNjAPB41Z20g+hXz8DTN3HJRrRk4OyWSsj4+Tuxj5pAhn7DWn4RdveLYvp+WkvyADwsHUMACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:25:24.751979Z","bundle_sha256":"4dae10755394a8b6be61e2e191f10a580c570afb447eb7f49e68a93691fd1b53"}}