{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TENPPA3VQVYU5ZFHLBIMDW7WRW","short_pith_number":"pith:TENPPA3V","canonical_record":{"source":{"id":"2505.24615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:08:13Z","cross_cats_sorted":[],"title_canon_sha256":"387fe4c7d92bab54cf5db221576a4170e71b2c66bde7108b24fd1c5a1b5b3a2a","abstract_canon_sha256":"52605d87aba3443d28786dbe3ca8e01436205c9e19cf5f35579e87f30cd9497d"},"schema_version":"1.0"},"canonical_sha256":"991af7837585714ee4a75850c1dbf68dbb2470e8132eeb61f14304bb3a4455eb","source":{"kind":"arxiv","id":"2505.24615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24615","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24615v1","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24615","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"pith_short_12","alias_value":"TENPPA3VQVYU","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"pith_short_16","alias_value":"TENPPA3VQVYU5ZFH","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"pith_short_8","alias_value":"TENPPA3V","created_at":"2026-07-05T11:12:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TENPPA3VQVYU5ZFHLBIMDW7WRW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:08:13Z","cross_cats_sorted":[],"title_canon_sha256":"387fe4c7d92bab54cf5db221576a4170e71b2c66bde7108b24fd1c5a1b5b3a2a","abstract_canon_sha256":"52605d87aba3443d28786dbe3ca8e01436205c9e19cf5f35579e87f30cd9497d"},"schema_version":"1.0"},"canonical_sha256":"991af7837585714ee4a75850c1dbf68dbb2470e8132eeb61f14304bb3a4455eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:53.383611Z","signature_b64":"j0vdvNY7ZrhVt7VeUalPUP/STGhFymkUNSc3r4Y167m4esUgNSJhG+gFAQIpWeYZBFmDLngimuTfPy0rgUvSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"991af7837585714ee4a75850c1dbf68dbb2470e8132eeb61f14304bb3a4455eb","last_reissued_at":"2026-07-05T11:12:53.383100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:53.383100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24615","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":"2026-07-05T11:12:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uaxo9/E3u9jzYsFaYZnkXx6LfhJZQkePz0nRcsw/i2uxLHyHuzSCEvhG3YBrc89W/55LdeVO2ttOkhMb2mviAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:06:14.271353Z"},"content_sha256":"e376b4f1e6a2a0d87eac9713107a5e63b556b0329010fc9323686cbc7882bd57","schema_version":"1.0","event_id":"sha256:e376b4f1e6a2a0d87eac9713107a5e63b556b0329010fc9323686cbc7882bd57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TENPPA3VQVYU5ZFHLBIMDW7WRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harnessing Large Language Models for Scientific Novelty Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Erik Cambria, Soujanya Poria, Thanh-Son Nguyen, Yan Liu, Zonglin Yang","submitted_at":"2025-05-30T14:08:13Z","abstract_excerpt":"In an era of exponential scientific growth, identifying novel research ideas is crucial and challenging in academia. Despite potential, the lack of an appropriate benchmark dataset hinders the research of novelty detection. More importantly, simply adopting existing NLP technologies, e.g., retrieving and then cross-checking, is not a one-size-fits-all solution due to the gap between textual similarity and idea conception. In this paper, we propose to harness large language models (LLMs) for scientific novelty detection (ND), associated with two new datasets in marketing and NLP domains. To con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24615","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/2505.24615/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":"2026-07-05T11:12:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCBNOIwMX4JKGZ27cI8HsKU9/+y5SXVphSNqmBb2l/lAKMXh4hXTgzwnJW6cOQfVHub5GMYE2zyJljWGodt7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:06:14.271988Z"},"content_sha256":"01d005bb210799fa9e943c6daf82b21f19d7443b117a5402a3d8e874b78cfb75","schema_version":"1.0","event_id":"sha256:01d005bb210799fa9e943c6daf82b21f19d7443b117a5402a3d8e874b78cfb75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TENPPA3VQVYU5ZFHLBIMDW7WRW/bundle.json","state_url":"https://pith.science/pith/TENPPA3VQVYU5ZFHLBIMDW7WRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TENPPA3VQVYU5ZFHLBIMDW7WRW/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":"2026-08-09T13:06:14Z","links":{"resolver":"https://pith.science/pith/TENPPA3VQVYU5ZFHLBIMDW7WRW","bundle":"https://pith.science/pith/TENPPA3VQVYU5ZFHLBIMDW7WRW/bundle.json","state":"https://pith.science/pith/TENPPA3VQVYU5ZFHLBIMDW7WRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TENPPA3VQVYU5ZFHLBIMDW7WRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TENPPA3VQVYU5ZFHLBIMDW7WRW","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":"52605d87aba3443d28786dbe3ca8e01436205c9e19cf5f35579e87f30cd9497d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:08:13Z","title_canon_sha256":"387fe4c7d92bab54cf5db221576a4170e71b2c66bde7108b24fd1c5a1b5b3a2a"},"schema_version":"1.0","source":{"id":"2505.24615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24615","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24615v1","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24615","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"pith_short_12","alias_value":"TENPPA3VQVYU","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"pith_short_16","alias_value":"TENPPA3VQVYU5ZFH","created_at":"2026-07-05T11:12:53Z"},{"alias_kind":"pith_short_8","alias_value":"TENPPA3V","created_at":"2026-07-05T11:12:53Z"}],"graph_snapshots":[{"event_id":"sha256:01d005bb210799fa9e943c6daf82b21f19d7443b117a5402a3d8e874b78cfb75","target":"graph","created_at":"2026-07-05T11:12:53Z","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/2505.24615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In an era of exponential scientific growth, identifying novel research ideas is crucial and challenging in academia. Despite potential, the lack of an appropriate benchmark dataset hinders the research of novelty detection. More importantly, simply adopting existing NLP technologies, e.g., retrieving and then cross-checking, is not a one-size-fits-all solution due to the gap between textual similarity and idea conception. In this paper, we propose to harness large language models (LLMs) for scientific novelty detection (ND), associated with two new datasets in marketing and NLP domains. To con","authors_text":"Erik Cambria, Soujanya Poria, Thanh-Son Nguyen, Yan Liu, Zonglin Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:08:13Z","title":"Harnessing Large Language Models for Scientific Novelty Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24615","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:e376b4f1e6a2a0d87eac9713107a5e63b556b0329010fc9323686cbc7882bd57","target":"record","created_at":"2026-07-05T11:12:53Z","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":"52605d87aba3443d28786dbe3ca8e01436205c9e19cf5f35579e87f30cd9497d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:08:13Z","title_canon_sha256":"387fe4c7d92bab54cf5db221576a4170e71b2c66bde7108b24fd1c5a1b5b3a2a"},"schema_version":"1.0","source":{"id":"2505.24615","kind":"arxiv","version":1}},"canonical_sha256":"991af7837585714ee4a75850c1dbf68dbb2470e8132eeb61f14304bb3a4455eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"991af7837585714ee4a75850c1dbf68dbb2470e8132eeb61f14304bb3a4455eb","first_computed_at":"2026-07-05T11:12:53.383100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:53.383100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j0vdvNY7ZrhVt7VeUalPUP/STGhFymkUNSc3r4Y167m4esUgNSJhG+gFAQIpWeYZBFmDLngimuTfPy0rgUvSDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:53.383611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e376b4f1e6a2a0d87eac9713107a5e63b556b0329010fc9323686cbc7882bd57","sha256:01d005bb210799fa9e943c6daf82b21f19d7443b117a5402a3d8e874b78cfb75"],"state_sha256":"fdd902cf2a922ddf06e3d9505eeb225223bbbe97648c5738b5685eb042b72024"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h06Qu/VnwNYqFjHYZiiC5el+YqwiNJ58pCoGKo1PRfwJqn0U6iTh7tGNaAhY7Csejv3maHxZy0E0St6DnvO8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:06:14.276008Z","bundle_sha256":"962bb9278595e8c57e575b4b7e93a92a61995625cddf6d057f0f609f23f4262b"}}