{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HGPUSP2DGPO6L2IXSM2ZY6OVRP","short_pith_number":"pith:HGPUSP2D","schema_version":"1.0","canonical_sha256":"399f493f4333dde5e91793359c79d58be529bbe537f96afdaeaf89a53b124aaa","source":{"kind":"arxiv","id":"2410.19494","version":3},"attestation_state":"computed","paper":{"title":"Graph Linearization Methods for Reasoning on Graphs with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christos Xypolopoulos, Giannis Nikolentzos, Giorgos Stamou, Guokan Shang, Hadi Abdine, Iakovos Evdaimon, Michail Chatzianastasis, Michalis Vazirgiannis, Xiao Fei","submitted_at":"2024-10-25T11:51:37Z","abstract_excerpt":"Large language models have evolved to process multiple modalities beyond text, such as images and audio, which motivates us to explore how to effectively leverage them for graph reasoning tasks. The key question, therefore, is how to transform graphs into linear sequences of tokens, a process we term \"graph linearization\", so that LLMs can handle graphs naturally. We consider that graphs should be linearized meaningfully to reflect certain properties of natural language text, such as local dependency and global alignment, in order to ease contemporary LLMs, trained on trillions of textual toke"},"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":"2410.19494","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T11:51:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aebb3ef74cf38b01efe6998d346b45e83d56ec10d29f520cbb3dfb3320c1fb06","abstract_canon_sha256":"d5b4d5947b796e818531f4c800603a038069d2015ca3aebc05fd40247597c02d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:44.494041Z","signature_b64":"R/s2uzV/0gxberlqzcIC4JknyHMAPs4lhbcvC2Liw1m41qK6SaQL9CGoqdgTrflvNvqmiCKRimuL0jaausXwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"399f493f4333dde5e91793359c79d58be529bbe537f96afdaeaf89a53b124aaa","last_reissued_at":"2026-07-05T11:26:44.493548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:44.493548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Linearization Methods for Reasoning on Graphs with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christos Xypolopoulos, Giannis Nikolentzos, Giorgos Stamou, Guokan Shang, Hadi Abdine, Iakovos Evdaimon, Michail Chatzianastasis, Michalis Vazirgiannis, Xiao Fei","submitted_at":"2024-10-25T11:51:37Z","abstract_excerpt":"Large language models have evolved to process multiple modalities beyond text, such as images and audio, which motivates us to explore how to effectively leverage them for graph reasoning tasks. The key question, therefore, is how to transform graphs into linear sequences of tokens, a process we term \"graph linearization\", so that LLMs can handle graphs naturally. We consider that graphs should be linearized meaningfully to reflect certain properties of natural language text, such as local dependency and global alignment, in order to ease contemporary LLMs, trained on trillions of textual toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19494","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/2410.19494/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":"2410.19494","created_at":"2026-07-05T11:26:44.493608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19494v3","created_at":"2026-07-05T11:26:44.493608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19494","created_at":"2026-07-05T11:26:44.493608+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGPUSP2DGPO6","created_at":"2026-07-05T11:26:44.493608+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGPUSP2DGPO6L2IX","created_at":"2026-07-05T11:26:44.493608+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGPUSP2D","created_at":"2026-07-05T11:26:44.493608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15633","citing_title":"Formalizing and Mitigating Structural Distortion in LLM Attention for Graph Reasoning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06865","citing_title":"Are Large Language Models Suitable for Graph Computation? Progress and Prospects","ref_index":253,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08458","citing_title":"A document is worth a structured record: Principled inductive bias design for document recognition","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP","json":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP.json","graph_json":"https://pith.science/api/pith-number/HGPUSP2DGPO6L2IXSM2ZY6OVRP/graph.json","events_json":"https://pith.science/api/pith-number/HGPUSP2DGPO6L2IXSM2ZY6OVRP/events.json","paper":"https://pith.science/paper/HGPUSP2D"},"agent_actions":{"view_html":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP","download_json":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP.json","view_paper":"https://pith.science/paper/HGPUSP2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19494&json=true","fetch_graph":"https://pith.science/api/pith-number/HGPUSP2DGPO6L2IXSM2ZY6OVRP/graph.json","fetch_events":"https://pith.science/api/pith-number/HGPUSP2DGPO6L2IXSM2ZY6OVRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP/action/storage_attestation","attest_author":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP/action/author_attestation","sign_citation":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP/action/citation_signature","submit_replication":"https://pith.science/pith/HGPUSP2DGPO6L2IXSM2ZY6OVRP/action/replication_record"}},"created_at":"2026-07-05T11:26:44.493608+00:00","updated_at":"2026-07-05T11:26:44.493608+00:00"}