{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3SPSYPFVZVRWM7CLM5FPKCTAPI","short_pith_number":"pith:3SPSYPFV","canonical_record":{"source":{"id":"2310.00305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T08:33:04Z","cross_cats_sorted":[],"title_canon_sha256":"f22100d45af670afae06f422bb5a83fb3fe144d258a0cf8cdb77753c94c259d5","abstract_canon_sha256":"9b33af568875985ea93a81a76ee04778409b6368ef799c0dda84912762bbe518"},"schema_version":"1.0"},"canonical_sha256":"dc9f2c3cb5cd63667c4b674af50a607a2da21e23694ea4596a0b29294c49358b","source":{"kind":"arxiv","id":"2310.00305","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00305","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00305v1","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00305","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_12","alias_value":"3SPSYPFVZVRW","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_16","alias_value":"3SPSYPFVZVRWM7CL","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_8","alias_value":"3SPSYPFV","created_at":"2026-07-05T06:56:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3SPSYPFVZVRWM7CLM5FPKCTAPI","target":"record","payload":{"canonical_record":{"source":{"id":"2310.00305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T08:33:04Z","cross_cats_sorted":[],"title_canon_sha256":"f22100d45af670afae06f422bb5a83fb3fe144d258a0cf8cdb77753c94c259d5","abstract_canon_sha256":"9b33af568875985ea93a81a76ee04778409b6368ef799c0dda84912762bbe518"},"schema_version":"1.0"},"canonical_sha256":"dc9f2c3cb5cd63667c4b674af50a607a2da21e23694ea4596a0b29294c49358b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:03.932276Z","signature_b64":"TTdoTziSKd3cLiccls7/xWJNs60S2Wb+oPCbPskKcp7D1+MYdNUsffJepJJZt0jNcDyAY4vRatWMCfee8D9TCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc9f2c3cb5cd63667c4b674af50a607a2da21e23694ea4596a0b29294c49358b","last_reissued_at":"2026-07-05T06:56:03.931870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:03.931870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.00305","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":"2026-07-05T06:56:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dw6fQs5RY37ShIItzVzS6nhUkWsUoDBqhZHik0NrpTxUGd+6tsQkmX/F7WIdyipZURX4/kPjZBfwnIqD1bnDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:37:25.520561Z"},"content_sha256":"29d97a0b2eaea80ce12a4eec6d0460357ed658148fc4221da3555b3c834ca529","schema_version":"1.0","event_id":"sha256:29d97a0b2eaea80ce12a4eec6d0460357ed658148fc4221da3555b3c834ca529"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3SPSYPFVZVRWM7CLM5FPKCTAPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Wei Gao, Xuan Zhang","submitted_at":"2023-09-30T08:33:04Z","abstract_excerpt":"While large pre-trained language models (LLMs) have shown their impressive capabilities in various NLP tasks, they are still under-explored in the misinformation domain. In this paper, we examine LLMs with in-context learning (ICL) for news claim verification, and find that only with 4-shot demonstration examples, the performance of several prompting methods can be comparable with previous supervised models. To further boost performance, we introduce a Hierarchical Step-by-Step (HiSS) prompting method which directs LLMs to separate a claim into several subclaims and then verify each of them vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00305","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/2310.00305/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":"2026-07-05T06:56:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0v2j4mowU2voQ6t9r3oD0glpujU+/kMiKEYHQEtUtL+92RZGH93Q/rLD7uSkx9FGOCJw2Rmbb0Hhmust5GGECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:37:25.521517Z"},"content_sha256":"93cfba3a0dcd1f4228a3132e36ab5b6ddb16deeeb3aa9bb887f3fa7fb7d60d62","schema_version":"1.0","event_id":"sha256:93cfba3a0dcd1f4228a3132e36ab5b6ddb16deeeb3aa9bb887f3fa7fb7d60d62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3SPSYPFVZVRWM7CLM5FPKCTAPI/bundle.json","state_url":"https://pith.science/pith/3SPSYPFVZVRWM7CLM5FPKCTAPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3SPSYPFVZVRWM7CLM5FPKCTAPI/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":"2026-08-07T09:37:25Z","links":{"resolver":"https://pith.science/pith/3SPSYPFVZVRWM7CLM5FPKCTAPI","bundle":"https://pith.science/pith/3SPSYPFVZVRWM7CLM5FPKCTAPI/bundle.json","state":"https://pith.science/pith/3SPSYPFVZVRWM7CLM5FPKCTAPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3SPSYPFVZVRWM7CLM5FPKCTAPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3SPSYPFVZVRWM7CLM5FPKCTAPI","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":"9b33af568875985ea93a81a76ee04778409b6368ef799c0dda84912762bbe518","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T08:33:04Z","title_canon_sha256":"f22100d45af670afae06f422bb5a83fb3fe144d258a0cf8cdb77753c94c259d5"},"schema_version":"1.0","source":{"id":"2310.00305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00305","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00305v1","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00305","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_12","alias_value":"3SPSYPFVZVRW","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_16","alias_value":"3SPSYPFVZVRWM7CL","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_8","alias_value":"3SPSYPFV","created_at":"2026-07-05T06:56:03Z"}],"graph_snapshots":[{"event_id":"sha256:93cfba3a0dcd1f4228a3132e36ab5b6ddb16deeeb3aa9bb887f3fa7fb7d60d62","target":"graph","created_at":"2026-07-05T06:56:03Z","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/2310.00305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large pre-trained language models (LLMs) have shown their impressive capabilities in various NLP tasks, they are still under-explored in the misinformation domain. In this paper, we examine LLMs with in-context learning (ICL) for news claim verification, and find that only with 4-shot demonstration examples, the performance of several prompting methods can be comparable with previous supervised models. To further boost performance, we introduce a Hierarchical Step-by-Step (HiSS) prompting method which directs LLMs to separate a claim into several subclaims and then verify each of them vi","authors_text":"Wei Gao, Xuan Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T08:33:04Z","title":"Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00305","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":"sha256:29d97a0b2eaea80ce12a4eec6d0460357ed658148fc4221da3555b3c834ca529","target":"record","created_at":"2026-07-05T06:56:03Z","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":"9b33af568875985ea93a81a76ee04778409b6368ef799c0dda84912762bbe518","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T08:33:04Z","title_canon_sha256":"f22100d45af670afae06f422bb5a83fb3fe144d258a0cf8cdb77753c94c259d5"},"schema_version":"1.0","source":{"id":"2310.00305","kind":"arxiv","version":1}},"canonical_sha256":"dc9f2c3cb5cd63667c4b674af50a607a2da21e23694ea4596a0b29294c49358b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc9f2c3cb5cd63667c4b674af50a607a2da21e23694ea4596a0b29294c49358b","first_computed_at":"2026-07-05T06:56:03.931870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:03.931870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TTdoTziSKd3cLiccls7/xWJNs60S2Wb+oPCbPskKcp7D1+MYdNUsffJepJJZt0jNcDyAY4vRatWMCfee8D9TCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:03.932276Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29d97a0b2eaea80ce12a4eec6d0460357ed658148fc4221da3555b3c834ca529","sha256:93cfba3a0dcd1f4228a3132e36ab5b6ddb16deeeb3aa9bb887f3fa7fb7d60d62"],"state_sha256":"3693f4019b09bcf3f5d83b4e9ebfbd46850abc67c877c4637d4880b686871cba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i0PImL3Npjg/i0SDrC8wTAesY7WgFw2UyRaoEs2emL14tHaLzDN/bCwW7tUAVAl4mpKNc8F1zmJZmoJxUCryDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:37:25.527225Z","bundle_sha256":"8316efd1aca6724e9c06eda4dbc2febba03570a0d50771f2d68fd92864cf8f1e"}}