{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RLAQZNAZRMCTCGWUFRSWULUI6U","short_pith_number":"pith:RLAQZNAZ","canonical_record":{"source":{"id":"2309.16595","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T16:58:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be6fe334b7865f2e63ad36b24c3e002858ada38c61f39f6cd2c1e7b4252f262d","abstract_canon_sha256":"a6420d1e964679712e81840c88a7a0f5c0f470295fd6615bf85c38916b7ed1a0"},"schema_version":"1.0"},"canonical_sha256":"8ac10cb4198b05311ad42c656a2e88f516511e3ef8027847bdcb307cdbb08852","source":{"kind":"arxiv","id":"2309.16595","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16595","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16595v4","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16595","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_12","alias_value":"RLAQZNAZRMCT","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_16","alias_value":"RLAQZNAZRMCTCGWU","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_8","alias_value":"RLAQZNAZ","created_at":"2026-07-05T08:32:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RLAQZNAZRMCTCGWUFRSWULUI6U","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16595","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T16:58:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be6fe334b7865f2e63ad36b24c3e002858ada38c61f39f6cd2c1e7b4252f262d","abstract_canon_sha256":"a6420d1e964679712e81840c88a7a0f5c0f470295fd6615bf85c38916b7ed1a0"},"schema_version":"1.0"},"canonical_sha256":"8ac10cb4198b05311ad42c656a2e88f516511e3ef8027847bdcb307cdbb08852","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:09.229396Z","signature_b64":"udaOpUdmiH91UPude2t9Yj+FRj4Vvhm1r1kmCfByxXwjFUjCFy//CalCELVPholMOmlUxyAicej1I36Ad63RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ac10cb4198b05311ad42c656a2e88f516511e3ef8027847bdcb307cdbb08852","last_reissued_at":"2026-07-05T08:32:09.228890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:09.228890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16595","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IY+07pcJmd0S3JVWyleZquEcmYIX/moRlmcWwQKoiIhzik35osC1IDz6gV58fwW1gleLrjpHrdmiGorjfaRnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:05:46.469348Z"},"content_sha256":"7454b85a3efc762f7472d7fa8457ec967aa33dacc7ae94dcfed3aeabbb40bd08","schema_version":"1.0","event_id":"sha256:7454b85a3efc762f7472d7fa8457ec967aa33dacc7ae94dcfed3aeabbb40bd08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RLAQZNAZRMCTCGWUFRSWULUI6U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaqi Ma, Jin Huang, Qiaozhu Mei, Xingjian Zhang","submitted_at":"2023-09-28T16:58:37Z","abstract_excerpt":"Large language models (LLMs) are gaining increasing attention for their capability to process graphs with rich text attributes, especially in a zero-shot fashion. Recent studies demonstrate that LLMs obtain decent text classification performance on common text-rich graph benchmarks, and the performance can be improved by appending encoded structural information as natural languages into prompts. We aim to understand why the incorporation of structural information inherent in graph data can improve the prediction performance of LLMs. First, we rule out the concern of data leakage by curating a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16595","kind":"arxiv","version":4},"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/2309.16595/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":"2026-07-05T08:32:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wjw3HVKjHMeox4EzisnynDnJKXArc57RztGfdxK1TkslwoQWFyvkF/Lke8tJbFlwifuWcRZHXXy62j9bd2g7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:05:46.470274Z"},"content_sha256":"94b0957470db141e3b0670f08389e7bc725270d991206b8005abd3289b8219ae","schema_version":"1.0","event_id":"sha256:94b0957470db141e3b0670f08389e7bc725270d991206b8005abd3289b8219ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLAQZNAZRMCTCGWUFRSWULUI6U/bundle.json","state_url":"https://pith.science/pith/RLAQZNAZRMCTCGWUFRSWULUI6U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLAQZNAZRMCTCGWUFRSWULUI6U/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":"2026-08-06T22:05:46Z","links":{"resolver":"https://pith.science/pith/RLAQZNAZRMCTCGWUFRSWULUI6U","bundle":"https://pith.science/pith/RLAQZNAZRMCTCGWUFRSWULUI6U/bundle.json","state":"https://pith.science/pith/RLAQZNAZRMCTCGWUFRSWULUI6U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLAQZNAZRMCTCGWUFRSWULUI6U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RLAQZNAZRMCTCGWUFRSWULUI6U","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":"a6420d1e964679712e81840c88a7a0f5c0f470295fd6615bf85c38916b7ed1a0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T16:58:37Z","title_canon_sha256":"be6fe334b7865f2e63ad36b24c3e002858ada38c61f39f6cd2c1e7b4252f262d"},"schema_version":"1.0","source":{"id":"2309.16595","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16595","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16595v4","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16595","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_12","alias_value":"RLAQZNAZRMCT","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_16","alias_value":"RLAQZNAZRMCTCGWU","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_8","alias_value":"RLAQZNAZ","created_at":"2026-07-05T08:32:09Z"}],"graph_snapshots":[{"event_id":"sha256:94b0957470db141e3b0670f08389e7bc725270d991206b8005abd3289b8219ae","target":"graph","created_at":"2026-07-05T08:32:09Z","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/2309.16595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are gaining increasing attention for their capability to process graphs with rich text attributes, especially in a zero-shot fashion. Recent studies demonstrate that LLMs obtain decent text classification performance on common text-rich graph benchmarks, and the performance can be improved by appending encoded structural information as natural languages into prompts. We aim to understand why the incorporation of structural information inherent in graph data can improve the prediction performance of LLMs. First, we rule out the concern of data leakage by curating a ","authors_text":"Jiaqi Ma, Jin Huang, Qiaozhu Mei, Xingjian Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T16:58:37Z","title":"Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16595","kind":"arxiv","version":4},"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":"sha256:7454b85a3efc762f7472d7fa8457ec967aa33dacc7ae94dcfed3aeabbb40bd08","target":"record","created_at":"2026-07-05T08:32:09Z","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":"a6420d1e964679712e81840c88a7a0f5c0f470295fd6615bf85c38916b7ed1a0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T16:58:37Z","title_canon_sha256":"be6fe334b7865f2e63ad36b24c3e002858ada38c61f39f6cd2c1e7b4252f262d"},"schema_version":"1.0","source":{"id":"2309.16595","kind":"arxiv","version":4}},"canonical_sha256":"8ac10cb4198b05311ad42c656a2e88f516511e3ef8027847bdcb307cdbb08852","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ac10cb4198b05311ad42c656a2e88f516511e3ef8027847bdcb307cdbb08852","first_computed_at":"2026-07-05T08:32:09.228890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:09.228890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"udaOpUdmiH91UPude2t9Yj+FRj4Vvhm1r1kmCfByxXwjFUjCFy//CalCELVPholMOmlUxyAicej1I36Ad63RDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:09.229396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16595","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7454b85a3efc762f7472d7fa8457ec967aa33dacc7ae94dcfed3aeabbb40bd08","sha256:94b0957470db141e3b0670f08389e7bc725270d991206b8005abd3289b8219ae"],"state_sha256":"f420749ce81f7524813c45f57d2e148857703de98f186d13d2265ab38f016af8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPUfdcdpQ0jB+mnF7QMEJCPuE3vRK5IGAd59F6/1TaPhmDBHs/kWT6je0DWRzsFKXk6f7yL2XJH2prc2NEWWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:05:46.495077Z","bundle_sha256":"99f921bf5ef564d606e8905834abb8dba10a058fbeab342014796e427b859bf8"}}