{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C2FJGZ56DXPBA57I5YVWAFI7VE","short_pith_number":"pith:C2FJGZ56","schema_version":"1.0","canonical_sha256":"168a9367be1dde1077e8ee2b60151fa925fd10c5a35fdc8f7a96533f53949255","source":{"kind":"arxiv","id":"2509.00740","version":1},"attestation_state":"computed","paper":{"title":"Efficient Graph Understanding with LLMs via Structured Context Injection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Govind Waghmare, Sonia Gupta, Srikanta Bedathur, Sumedh BG","submitted_at":"2025-08-31T08:07:56Z","abstract_excerpt":"Large Language Models (LLMs) have shown strong capabilities in solving problems across domains, including graph-related tasks traditionally addressed by symbolic or algorithmic methods. In this work, we present a framework for structured context injection, where task-specific information is systematically embedded in the input to guide LLMs in solving a wide range of graph problems. Our method does not require fine-tuning of LLMs, making it cost-efficient and lightweight. We observe that certain graph reasoning tasks remain challenging for LLMs unless they are mapped to conceptually grounded r"},"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":"2509.00740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-31T08:07:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb522a946837a44627b2b97cbfb8c835b25ea04002c2a6f6e05f33a3a93e8d2e","abstract_canon_sha256":"f20bef6585736cdcf356d70eaf93f80a1b38522f1d41ec9fb9c51a4c0e2977d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:22.018368Z","signature_b64":"aSzHKFRfBUBwoPbNNrXxbiQ+sYktehDh0JrTi0tVk8hXt1RGaE2BB3MZlUfBaZ/h+mGzD8lCZ9Fzl4Gz+SwLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"168a9367be1dde1077e8ee2b60151fa925fd10c5a35fdc8f7a96533f53949255","last_reissued_at":"2026-07-05T12:02:22.017866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:22.017866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Graph Understanding with LLMs via Structured Context Injection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Govind Waghmare, Sonia Gupta, Srikanta Bedathur, Sumedh BG","submitted_at":"2025-08-31T08:07:56Z","abstract_excerpt":"Large Language Models (LLMs) have shown strong capabilities in solving problems across domains, including graph-related tasks traditionally addressed by symbolic or algorithmic methods. In this work, we present a framework for structured context injection, where task-specific information is systematically embedded in the input to guide LLMs in solving a wide range of graph problems. Our method does not require fine-tuning of LLMs, making it cost-efficient and lightweight. We observe that certain graph reasoning tasks remain challenging for LLMs unless they are mapped to conceptually grounded r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00740","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/2509.00740/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":"2509.00740","created_at":"2026-07-05T12:02:22.017918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00740v1","created_at":"2026-07-05T12:02:22.017918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00740","created_at":"2026-07-05T12:02:22.017918+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2FJGZ56DXPB","created_at":"2026-07-05T12:02:22.017918+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2FJGZ56DXPBA57I","created_at":"2026-07-05T12:02:22.017918+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2FJGZ56","created_at":"2026-07-05T12:02:22.017918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE","json":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE.json","graph_json":"https://pith.science/api/pith-number/C2FJGZ56DXPBA57I5YVWAFI7VE/graph.json","events_json":"https://pith.science/api/pith-number/C2FJGZ56DXPBA57I5YVWAFI7VE/events.json","paper":"https://pith.science/paper/C2FJGZ56"},"agent_actions":{"view_html":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE","download_json":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE.json","view_paper":"https://pith.science/paper/C2FJGZ56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00740&json=true","fetch_graph":"https://pith.science/api/pith-number/C2FJGZ56DXPBA57I5YVWAFI7VE/graph.json","fetch_events":"https://pith.science/api/pith-number/C2FJGZ56DXPBA57I5YVWAFI7VE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE/action/storage_attestation","attest_author":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE/action/author_attestation","sign_citation":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE/action/citation_signature","submit_replication":"https://pith.science/pith/C2FJGZ56DXPBA57I5YVWAFI7VE/action/replication_record"}},"created_at":"2026-07-05T12:02:22.017918+00:00","updated_at":"2026-07-05T12:02:22.017918+00:00"}