{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L5AGRODLKZCUNDUJPDDQ36CHEN","short_pith_number":"pith:L5AGRODL","canonical_record":{"source":{"id":"2502.07340","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T08:05:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6dc3b46fbf647b7c7e9c55ae88b4fa04663647bb9783bd1604bd0966ece7d83d","abstract_canon_sha256":"aacd67b574fba835e00390c1c52ec42cac5736413300e579132a42363fa812c2"},"schema_version":"1.0"},"canonical_sha256":"5f4068b86b5645468e8978c70df847237f0f54a3076e8ee6b11d3740f58378a1","source":{"kind":"arxiv","id":"2502.07340","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07340","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07340v3","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07340","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"L5AGRODLKZCU","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"L5AGRODLKZCUNDUJ","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"L5AGRODL","created_at":"2026-07-05T11:09:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L5AGRODLKZCUNDUJPDDQ36CHEN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07340","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T08:05:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6dc3b46fbf647b7c7e9c55ae88b4fa04663647bb9783bd1604bd0966ece7d83d","abstract_canon_sha256":"aacd67b574fba835e00390c1c52ec42cac5736413300e579132a42363fa812c2"},"schema_version":"1.0"},"canonical_sha256":"5f4068b86b5645468e8978c70df847237f0f54a3076e8ee6b11d3740f58378a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:08.017876Z","signature_b64":"uoKpuwiH8IYmWYvyuYKyhP1C5rYuFi8X/DaPo8ZsDJT5y/yGboYm1KWk3r8KDZAafQV+SICejY3vCKS9OytdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f4068b86b5645468e8978c70df847237f0f54a3076e8ee6b11d3740f58378a1","last_reissued_at":"2026-07-05T11:09:08.017390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:08.017390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07340","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":"2026-07-05T11:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++EI3AVVmN8fH0nl5pEo036IGrU2n4r8Nt4S78VePuM97Xv0lM9mKW16gzwUK9fvbkqfkZekFO5uk0q8SyIhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:16:00.617472Z"},"content_sha256":"45e8b8b8c7621d2c039a1dc5ac216c2d240fde5bca0109a84aa9b136393ff7aa","schema_version":"1.0","event_id":"sha256:45e8b8b8c7621d2c039a1dc5ac216c2d240fde5bca0109a84aa9b136393ff7aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L5AGRODLKZCUNDUJPDDQ36CHEN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Cheng Gao, Chen Qian, Fanchao Qi, Gang Chen, Haozhe Zhao, Kaikai An, Kangyang Luo, Maosong Sun, Shuzheng Si, Yuzhuo Bai, Zhitong Wang","submitted_at":"2025-02-11T08:05:56Z","abstract_excerpt":"Training LLMs on data containing unfamiliar knowledge during the instruction tuning stage can encourage hallucinations. To address this challenge, we introduce NOVA, a novel framework designed to identify high-quality data that aligns well with the LLM's learned knowledge to reduce hallucinations. NOVA includes Internal Consistency Probing (ICP) and Semantic Equivalence Identification (SEI) to measure how familiar the LLM is with instruction data. Specifically, ICP evaluates the LLM's understanding of the given instruction by calculating the tailored consistency among multiple self-generated r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07340","kind":"arxiv","version":3},"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/2502.07340/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":"2026-07-05T11:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WaMb7TeUifRXz2aSqc1vBEJeyoh3oXLfCIzD+weHBq3oI1hDfk/eNf12wkV5NqDAcEt1HrKBuJJGLCsmIfZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:16:00.618079Z"},"content_sha256":"61d2efa2814c9f2019af80e34a8ea9b18796d0df18e1101e5817e76f12f9a3ae","schema_version":"1.0","event_id":"sha256:61d2efa2814c9f2019af80e34a8ea9b18796d0df18e1101e5817e76f12f9a3ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L5AGRODLKZCUNDUJPDDQ36CHEN/bundle.json","state_url":"https://pith.science/pith/L5AGRODLKZCUNDUJPDDQ36CHEN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L5AGRODLKZCUNDUJPDDQ36CHEN/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":"2026-07-07T07:16:00Z","links":{"resolver":"https://pith.science/pith/L5AGRODLKZCUNDUJPDDQ36CHEN","bundle":"https://pith.science/pith/L5AGRODLKZCUNDUJPDDQ36CHEN/bundle.json","state":"https://pith.science/pith/L5AGRODLKZCUNDUJPDDQ36CHEN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L5AGRODLKZCUNDUJPDDQ36CHEN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L5AGRODLKZCUNDUJPDDQ36CHEN","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":"aacd67b574fba835e00390c1c52ec42cac5736413300e579132a42363fa812c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T08:05:56Z","title_canon_sha256":"6dc3b46fbf647b7c7e9c55ae88b4fa04663647bb9783bd1604bd0966ece7d83d"},"schema_version":"1.0","source":{"id":"2502.07340","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07340","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07340v3","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07340","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"L5AGRODLKZCU","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"L5AGRODLKZCUNDUJ","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"L5AGRODL","created_at":"2026-07-05T11:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:61d2efa2814c9f2019af80e34a8ea9b18796d0df18e1101e5817e76f12f9a3ae","target":"graph","created_at":"2026-07-05T11:09:08Z","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/2502.07340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training LLMs on data containing unfamiliar knowledge during the instruction tuning stage can encourage hallucinations. To address this challenge, we introduce NOVA, a novel framework designed to identify high-quality data that aligns well with the LLM's learned knowledge to reduce hallucinations. NOVA includes Internal Consistency Probing (ICP) and Semantic Equivalence Identification (SEI) to measure how familiar the LLM is with instruction data. Specifically, ICP evaluates the LLM's understanding of the given instruction by calculating the tailored consistency among multiple self-generated r","authors_text":"Baobao Chang, Cheng Gao, Chen Qian, Fanchao Qi, Gang Chen, Haozhe Zhao, Kaikai An, Kangyang Luo, Maosong Sun, Shuzheng Si, Yuzhuo Bai, Zhitong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T08:05:56Z","title":"Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07340","kind":"arxiv","version":3},"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":"sha256:45e8b8b8c7621d2c039a1dc5ac216c2d240fde5bca0109a84aa9b136393ff7aa","target":"record","created_at":"2026-07-05T11:09:08Z","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":"aacd67b574fba835e00390c1c52ec42cac5736413300e579132a42363fa812c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T08:05:56Z","title_canon_sha256":"6dc3b46fbf647b7c7e9c55ae88b4fa04663647bb9783bd1604bd0966ece7d83d"},"schema_version":"1.0","source":{"id":"2502.07340","kind":"arxiv","version":3}},"canonical_sha256":"5f4068b86b5645468e8978c70df847237f0f54a3076e8ee6b11d3740f58378a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f4068b86b5645468e8978c70df847237f0f54a3076e8ee6b11d3740f58378a1","first_computed_at":"2026-07-05T11:09:08.017390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:08.017390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uoKpuwiH8IYmWYvyuYKyhP1C5rYuFi8X/DaPo8ZsDJT5y/yGboYm1KWk3r8KDZAafQV+SICejY3vCKS9OytdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:08.017876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07340","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45e8b8b8c7621d2c039a1dc5ac216c2d240fde5bca0109a84aa9b136393ff7aa","sha256:61d2efa2814c9f2019af80e34a8ea9b18796d0df18e1101e5817e76f12f9a3ae"],"state_sha256":"cfc749f5b5d83b52e1738f6ccb73211d974f0e40d5699d1d534aa2980a7b3aef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6k73uETrsxEJQHgysVulhRfOreEtovkbhkNFekzOVcy2pY2SfCwNFobXcwQrMH6dP6PLZVCL8//H7LihNiO+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:16:00.621250Z","bundle_sha256":"2b1d32f48489d000d99d32961cd26a498572fcd8a911adfa4b425db3c798d80f"}}