{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BYP3EDXS64SMWB6ENJ7UJJ2HWR","short_pith_number":"pith:BYP3EDXS","canonical_record":{"source":{"id":"2605.01482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:05:38Z","cross_cats_sorted":[],"title_canon_sha256":"71e14239f79f5c4f86636cb7a3888b965dfeb42fa3ba80670f22295bdb5a1e08","abstract_canon_sha256":"05a6525bd4ceedf8bbd193e91497d6ede74be7fd164567922e83a8be1297b8d8"},"schema_version":"1.0"},"canonical_sha256":"0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707","source":{"kind":"arxiv","id":"2605.01482","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01482","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01482v3","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01482","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"BYP3EDXS64SM","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"BYP3EDXS64SMWB6E","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"BYP3EDXS","created_at":"2026-06-24T01:14:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BYP3EDXS64SMWB6ENJ7UJJ2HWR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.01482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:05:38Z","cross_cats_sorted":[],"title_canon_sha256":"71e14239f79f5c4f86636cb7a3888b965dfeb42fa3ba80670f22295bdb5a1e08","abstract_canon_sha256":"05a6525bd4ceedf8bbd193e91497d6ede74be7fd164567922e83a8be1297b8d8"},"schema_version":"1.0"},"canonical_sha256":"0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:28.377352Z","signature_b64":"7ZxLggv/TTyIkW6qzmmbQgAYT2vj5bsLTW0CM/BUVGIvoaBCysovJGHWlJGfLLY3ZSZFJGWE3Hvuty3Eyml2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707","last_reissued_at":"2026-06-24T01:14:28.376907Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:28.376907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.01482","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGqCSOEM7Mpi1FwKktsc7ngXaHtrCP+uCf6mlDAeWKlfEVApRFyDnPjn9A2bLKRzsLjkyli9FSA7oTGyY5kyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:02:42.299715Z"},"content_sha256":"87ac351b237f3de139e4666963d8c58b5950a3664713340b7ac31bf32d8549cc","schema_version":"1.0","event_id":"sha256:87ac351b237f3de139e4666963d8c58b5950a3664713340b7ac31bf32d8549cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BYP3EDXS64SMWB6ENJ7UJJ2HWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Askar Hamdulla, Baohua Zhang, Chunxiao Gao, Guotong Geng, Huaping Zhang, Juan Wang, Qiuchi Li, Quan Zhang, Shuai Lei, Yunbo Cao, Yunhan Bu, Zhunchen Luo","submitted_at":"2026-05-02T15:05:38Z","abstract_excerpt":"Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and fractured logical chains. Existing methods, while improving transparency via Chain-of-Thought , often lack explicit modeling of the structural dependencies between evidence and claims. In this work, we introduce an SCM-inspired framework that grounds reasoning in explicit directed dependency graphs, treating verification as a constructive structural reasoning process rather than full causal inference with interventi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework significantly outperforms state-of-the-art baselines, offering a reliable and interpretable solution for complex fact verification.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That explicitly modeling verification as a constructive causal inference process inside a structural causal model will produce more accurate and less hallucinated reasoning chains than standard chain-of-thought methods without introducing new modeling errors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"636cbfab7982b04d7adc59da33ab930f5dad07a1306fd149fdd29a6729eb74b1"},"source":{"id":"2605.01482","kind":"arxiv","version":3},"verdict":{"id":"28a751db-2df2-43aa-9963-4ae9fb9fa3ef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T02:12:57.703359Z","strongest_claim":"Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework significantly outperforms state-of-the-art baselines, offering a reliable and interpretable solution for complex fact verification.","one_line_summary":"SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That explicitly modeling verification as a constructive causal inference process inside a structural causal model will produce more accurate and less hallucinated reasoning chains than standard chain-of-thought methods without introducing new modeling errors.","pith_extraction_headline":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01482/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T17:41:07.373009Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:14:37.062627Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"24620f8e0b5165dab834ba9b01c0cec52100a6cea05b6ea10314ac478cc9440a"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e7e4508c0f2eaf08a47bda52dfce33fbe70217368bacb5502d074829a5e3046f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"28a751db-2df2-43aa-9963-4ae9fb9fa3ef"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wuBjoJFH3qi+JNWFlv1NgHYjM4W+rPv58BEVbYWPxwuF/2gv65fqlPRfFzmyZunMm/6NRjBma5XpiuFcyrJ9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:02:42.300575Z"},"content_sha256":"74efc93e7ca63672720bcbc902545234de5375bf9958daf748d1d2c291bff664","schema_version":"1.0","event_id":"sha256:74efc93e7ca63672720bcbc902545234de5375bf9958daf748d1d2c291bff664"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/bundle.json","state_url":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/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":"2026-08-04T06:02:42Z","links":{"resolver":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR","bundle":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/bundle.json","state":"https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BYP3EDXS64SMWB6ENJ7UJJ2HWR","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":"05a6525bd4ceedf8bbd193e91497d6ede74be7fd164567922e83a8be1297b8d8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:05:38Z","title_canon_sha256":"71e14239f79f5c4f86636cb7a3888b965dfeb42fa3ba80670f22295bdb5a1e08"},"schema_version":"1.0","source":{"id":"2605.01482","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01482","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01482v3","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01482","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"BYP3EDXS64SM","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"BYP3EDXS64SMWB6E","created_at":"2026-06-24T01:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"BYP3EDXS","created_at":"2026-06-24T01:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:74efc93e7ca63672720bcbc902545234de5375bf9958daf748d1d2c291bff664","target":"graph","created_at":"2026-06-24T01:14:28Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework significantly outperforms state-of-the-art baselines, offering a reliable and interpretable solution for complex fact verification."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That explicitly modeling verification as a constructive causal inference process inside a structural causal model will produce more accurate and less hallucinated reasoning chains than standard chain-of-thought methods without introducing new modeling errors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods."}],"snapshot_sha256":"636cbfab7982b04d7adc59da33ab930f5dad07a1306fd149fdd29a6729eb74b1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e7e4508c0f2eaf08a47bda52dfce33fbe70217368bacb5502d074829a5e3046f"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T17:41:07.373009Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:14:37.062627Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.01482/integrity.json","findings":[],"snapshot_sha256":"24620f8e0b5165dab834ba9b01c0cec52100a6cea05b6ea10314ac478cc9440a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and fractured logical chains. Existing methods, while improving transparency via Chain-of-Thought , often lack explicit modeling of the structural dependencies between evidence and claims. In this work, we introduce an SCM-inspired framework that grounds reasoning in explicit directed dependency graphs, treating verification as a constructive structural reasoning process rather than full causal inference with interventi","authors_text":"Askar Hamdulla, Baohua Zhang, Chunxiao Gao, Guotong Geng, Huaping Zhang, Juan Wang, Qiuchi Li, Quan Zhang, Shuai Lei, Yunbo Cao, Yunhan Bu, Zhunchen Luo","cross_cats":[],"headline":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:05:38Z","title":"Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.01482","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-11T02:12:57.703359Z","id":"28a751db-2df2-43aa-9963-4ae9fb9fa3ef","model_set":{"reader":"grok-4.3"},"one_line_summary":"SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods.","strongest_claim":"Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework significantly outperforms state-of-the-art baselines, offering a reliable and interpretable solution for complex fact verification.","weakest_assumption":"That explicitly modeling verification as a constructive causal inference process inside a structural causal model will produce more accurate and less hallucinated reasoning chains than standard chain-of-thought methods without introducing new modeling errors."}},"verdict_id":"28a751db-2df2-43aa-9963-4ae9fb9fa3ef"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:87ac351b237f3de139e4666963d8c58b5950a3664713340b7ac31bf32d8549cc","target":"record","created_at":"2026-06-24T01:14:28Z","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":"05a6525bd4ceedf8bbd193e91497d6ede74be7fd164567922e83a8be1297b8d8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:05:38Z","title_canon_sha256":"71e14239f79f5c4f86636cb7a3888b965dfeb42fa3ba80670f22295bdb5a1e08"},"schema_version":"1.0","source":{"id":"2605.01482","kind":"arxiv","version":3}},"canonical_sha256":"0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707","first_computed_at":"2026-06-24T01:14:28.376907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:28.376907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7ZxLggv/TTyIkW6qzmmbQgAYT2vj5bsLTW0CM/BUVGIvoaBCysovJGHWlJGfLLY3ZSZFJGWE3Hvuty3Eyml2Cg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:28.377352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01482","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87ac351b237f3de139e4666963d8c58b5950a3664713340b7ac31bf32d8549cc","sha256:74efc93e7ca63672720bcbc902545234de5375bf9958daf748d1d2c291bff664"],"state_sha256":"9c160a0e40016e3a595254f38cc9eba01634d36c26f59e8bce46f5eef65be6d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oyB3cmst7W8zlW9o2OuyGUoJ1o1029blVYYeaJ7ezU9mPDKXyd3daY87EqEbdJcxNxjXACt9a7ga+hKmwNwgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:02:42.306473Z","bundle_sha256":"c5bfc432118dd363158a875b202eb3b960ba8080e94d2b45b951625bdb558efb"}}