{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E7AY5UHFDOGDN7JM5UTTQUCP5L","short_pith_number":"pith:E7AY5UHF","canonical_record":{"source":{"id":"2501.12975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T15:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"f6619c52d7452025965d6c634bc1facd43834295ece4d5866da718dc1d634657","abstract_canon_sha256":"e8337dba079fff75af312736935f1c3a24180ea70f53fc6d623511ee2faf4c79"},"schema_version":"1.0"},"canonical_sha256":"27c18ed0e51b8c36fd2ced2738504feae388539d99e7de0b05d9ef6e888736af","source":{"kind":"arxiv","id":"2501.12975","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12975","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12975v1","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12975","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"E7AY5UHFDOGD","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"E7AY5UHFDOGDN7JM","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"E7AY5UHF","created_at":"2026-07-05T10:04:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E7AY5UHFDOGDN7JM5UTTQUCP5L","target":"record","payload":{"canonical_record":{"source":{"id":"2501.12975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T15:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"f6619c52d7452025965d6c634bc1facd43834295ece4d5866da718dc1d634657","abstract_canon_sha256":"e8337dba079fff75af312736935f1c3a24180ea70f53fc6d623511ee2faf4c79"},"schema_version":"1.0"},"canonical_sha256":"27c18ed0e51b8c36fd2ced2738504feae388539d99e7de0b05d9ef6e888736af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:01.192136Z","signature_b64":"P5z3YymEfYYtxzTbHwRSVQfDYhIMK/B4KrUZ3iQCBfguADQjlpIDhk3OgPuh8PXbzMiYGzktUPVoMsN2/pdYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27c18ed0e51b8c36fd2ced2738504feae388539d99e7de0b05d9ef6e888736af","last_reissued_at":"2026-07-05T10:04:01.191587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:01.191587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.12975","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":"2026-07-05T10:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nw01qU10E6pzn+PDXoAHqi/OJChebFwjNExmkV4SW0sHACSi2EnrwUGyZUyl5NcukkCwL3PwC5+c7FqxU0fMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:01:09.729794Z"},"content_sha256":"c91b3d6ae12c201c1b5fa3ed3f90f52dddb9c5db82c40b435002ccaec6a0b067","schema_version":"1.0","event_id":"sha256:c91b3d6ae12c201c1b5fa3ed3f90f52dddb9c5db82c40b435002ccaec6a0b067"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E7AY5UHFDOGDN7JM5UTTQUCP5L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OnionEval: An Unified Evaluation of Fact-conflicting Hallucination for Small-Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benoit Boulet, Chongren Sun, Di Wu, Yuran Li","submitted_at":"2025-01-22T15:59:44Z","abstract_excerpt":"Large Language Models (LLMs) are highly capable but require significant computational resources for both training and inference. Within the LLM family, smaller models (those with fewer than 10 billion parameters) also perform well across various tasks. However, these smaller models share similar limitations to their larger counterparts, including the tendency to hallucinate. Despite the existence of many benchmarks to evaluate hallucination in LLMs, few have specifically focused on small LLMs (SLLMs). Additionally, SLLMs show widely varying performance across different benchmarks. In this pape"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12975","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/2501.12975/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":"2026-07-05T10:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jfSCpEBOOuckm7Bl8opwrPDoXN3jEifQeXhL3F5aWhJlB/GjKD6XFQXXu5vi+63AQc7uzvDibMNnMujrQhFaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:01:09.730733Z"},"content_sha256":"f61c4c2b5c769bf82022dd13edb3a10f72e3ede2fab4d4e5cc57ad6e588f7847","schema_version":"1.0","event_id":"sha256:f61c4c2b5c769bf82022dd13edb3a10f72e3ede2fab4d4e5cc57ad6e588f7847"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7AY5UHFDOGDN7JM5UTTQUCP5L/bundle.json","state_url":"https://pith.science/pith/E7AY5UHFDOGDN7JM5UTTQUCP5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7AY5UHFDOGDN7JM5UTTQUCP5L/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":"2026-08-11T12:01:09Z","links":{"resolver":"https://pith.science/pith/E7AY5UHFDOGDN7JM5UTTQUCP5L","bundle":"https://pith.science/pith/E7AY5UHFDOGDN7JM5UTTQUCP5L/bundle.json","state":"https://pith.science/pith/E7AY5UHFDOGDN7JM5UTTQUCP5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7AY5UHFDOGDN7JM5UTTQUCP5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E7AY5UHFDOGDN7JM5UTTQUCP5L","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":"e8337dba079fff75af312736935f1c3a24180ea70f53fc6d623511ee2faf4c79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T15:59:44Z","title_canon_sha256":"f6619c52d7452025965d6c634bc1facd43834295ece4d5866da718dc1d634657"},"schema_version":"1.0","source":{"id":"2501.12975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12975","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12975v1","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12975","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"E7AY5UHFDOGD","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"E7AY5UHFDOGDN7JM","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"E7AY5UHF","created_at":"2026-07-05T10:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:f61c4c2b5c769bf82022dd13edb3a10f72e3ede2fab4d4e5cc57ad6e588f7847","target":"graph","created_at":"2026-07-05T10:04:01Z","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/2501.12975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are highly capable but require significant computational resources for both training and inference. Within the LLM family, smaller models (those with fewer than 10 billion parameters) also perform well across various tasks. However, these smaller models share similar limitations to their larger counterparts, including the tendency to hallucinate. Despite the existence of many benchmarks to evaluate hallucination in LLMs, few have specifically focused on small LLMs (SLLMs). Additionally, SLLMs show widely varying performance across different benchmarks. In this pape","authors_text":"Benoit Boulet, Chongren Sun, Di Wu, Yuran Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T15:59:44Z","title":"OnionEval: An Unified Evaluation of Fact-conflicting Hallucination for Small-Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12975","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:c91b3d6ae12c201c1b5fa3ed3f90f52dddb9c5db82c40b435002ccaec6a0b067","target":"record","created_at":"2026-07-05T10:04:01Z","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":"e8337dba079fff75af312736935f1c3a24180ea70f53fc6d623511ee2faf4c79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T15:59:44Z","title_canon_sha256":"f6619c52d7452025965d6c634bc1facd43834295ece4d5866da718dc1d634657"},"schema_version":"1.0","source":{"id":"2501.12975","kind":"arxiv","version":1}},"canonical_sha256":"27c18ed0e51b8c36fd2ced2738504feae388539d99e7de0b05d9ef6e888736af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27c18ed0e51b8c36fd2ced2738504feae388539d99e7de0b05d9ef6e888736af","first_computed_at":"2026-07-05T10:04:01.191587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:01.191587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P5z3YymEfYYtxzTbHwRSVQfDYhIMK/B4KrUZ3iQCBfguADQjlpIDhk3OgPuh8PXbzMiYGzktUPVoMsN2/pdYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:01.192136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c91b3d6ae12c201c1b5fa3ed3f90f52dddb9c5db82c40b435002ccaec6a0b067","sha256:f61c4c2b5c769bf82022dd13edb3a10f72e3ede2fab4d4e5cc57ad6e588f7847"],"state_sha256":"985406a0b220cd8267aec005e24f9c03106ba474ba1e8f4d7f8d3499d988fad9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jde/xnpPCiHmkLrfAwOqUDNBuZrfu8Al22/C5AcZXE5xlA6XAufHdot9QxxGUNJn702sO1OPfF+8seL/jYLEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:01:09.750833Z","bundle_sha256":"eae8551e5137de7d66bfb7fb8d0b06129c67284b9facc99c5ce51ce4dfbef674"}}