{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I2YKE3AZWXHH56JCWVTTRN5NIG","short_pith_number":"pith:I2YKE3AZ","schema_version":"1.0","canonical_sha256":"46b0a26c19b5ce7ef922b56738b7ad4194201588c31b7f2f1d3549b2f415b219","source":{"kind":"arxiv","id":"2501.14427","version":3},"attestation_state":"computed","paper":{"title":"GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Better","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingce Wang, Hanlin Xue, Tong Mo, Weiping Li, Xu Chu, Zhijie Tan","submitted_at":"2025-01-24T11:55:57Z","abstract_excerpt":"The success of Large Language Models (LLMs) in various domains has led researchers to apply them to graph-related problems by converting graph data into natural language text. However, unlike graph data, natural language inherently has sequential order. We observe a counter-intuitive fact that when the order of nodes or edges in the natural language description of a graph is shuffled, despite describing the same graph, model performance fluctuates between high performance and random guessing. Additionally, due to LLMs' limited input context length, current methods typically randomly sample nei"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.14427","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T11:55:57Z","cross_cats_sorted":[],"title_canon_sha256":"ed4862f1ccd989e9576d1c68a3e816b6abea445800a7df5a41f29e9ae289e42b","abstract_canon_sha256":"8bdd648f17d2b70173e6353a467c8599415f2d835be13e5ff3667d3480a96240"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:07.540061Z","signature_b64":"FbbeGM9tn+l4LSJVGub5gKL2ZmUkXyHQhGHpZTsD68hdQrOhLiPVIDfmaI/Jp2oCE2Y0giHgDyBFMfD2UIZ3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46b0a26c19b5ce7ef922b56738b7ad4194201588c31b7f2f1d3549b2f415b219","last_reissued_at":"2026-07-05T10:13:07.539424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:07.539424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Better","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingce Wang, Hanlin Xue, Tong Mo, Weiping Li, Xu Chu, Zhijie Tan","submitted_at":"2025-01-24T11:55:57Z","abstract_excerpt":"The success of Large Language Models (LLMs) in various domains has led researchers to apply them to graph-related problems by converting graph data into natural language text. However, unlike graph data, natural language inherently has sequential order. We observe a counter-intuitive fact that when the order of nodes or edges in the natural language description of a graph is shuffled, despite describing the same graph, model performance fluctuates between high performance and random guessing. Additionally, due to LLMs' limited input context length, current methods typically randomly sample nei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14427","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/2501.14427/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.14427","created_at":"2026-07-05T10:13:07.539502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14427v3","created_at":"2026-07-05T10:13:07.539502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14427","created_at":"2026-07-05T10:13:07.539502+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2YKE3AZWXHH","created_at":"2026-07-05T10:13:07.539502+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2YKE3AZWXHH56JC","created_at":"2026-07-05T10:13:07.539502+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2YKE3AZ","created_at":"2026-07-05T10:13:07.539502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11974","citing_title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG","json":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG.json","graph_json":"https://pith.science/api/pith-number/I2YKE3AZWXHH56JCWVTTRN5NIG/graph.json","events_json":"https://pith.science/api/pith-number/I2YKE3AZWXHH56JCWVTTRN5NIG/events.json","paper":"https://pith.science/paper/I2YKE3AZ"},"agent_actions":{"view_html":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG","download_json":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG.json","view_paper":"https://pith.science/paper/I2YKE3AZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14427&json=true","fetch_graph":"https://pith.science/api/pith-number/I2YKE3AZWXHH56JCWVTTRN5NIG/graph.json","fetch_events":"https://pith.science/api/pith-number/I2YKE3AZWXHH56JCWVTTRN5NIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG/action/storage_attestation","attest_author":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG/action/author_attestation","sign_citation":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG/action/citation_signature","submit_replication":"https://pith.science/pith/I2YKE3AZWXHH56JCWVTTRN5NIG/action/replication_record"}},"created_at":"2026-07-05T10:13:07.539502+00:00","updated_at":"2026-07-05T10:13:07.539502+00:00"}