{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JGZD5L3ZIJRMUXNNU65HNBSYVE","short_pith_number":"pith:JGZD5L3Z","canonical_record":{"source":{"id":"2402.05862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T17:51:44Z","cross_cats_sorted":["cs.AI","cs.SI","stat.ML"],"title_canon_sha256":"40df187f5a3f87e954e9ebe819422fb9594b1c5f46e7730838d9554c55e696eb","abstract_canon_sha256":"2a9fbaee99d4fb82efc0ac0e1684c86fe188c662c38e15056b3449a9c7a01121"},"schema_version":"1.0"},"canonical_sha256":"49b23eaf794262ca5dada7ba768658a934124fa64f91f0d42b02c76fd44c7751","source":{"kind":"arxiv","id":"2402.05862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05862","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05862v1","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05862","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"JGZD5L3ZIJRM","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_16","alias_value":"JGZD5L3ZIJRMUXNN","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_8","alias_value":"JGZD5L3Z","created_at":"2026-07-05T07:43:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JGZD5L3ZIJRMUXNNU65HNBSYVE","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T17:51:44Z","cross_cats_sorted":["cs.AI","cs.SI","stat.ML"],"title_canon_sha256":"40df187f5a3f87e954e9ebe819422fb9594b1c5f46e7730838d9554c55e696eb","abstract_canon_sha256":"2a9fbaee99d4fb82efc0ac0e1684c86fe188c662c38e15056b3449a9c7a01121"},"schema_version":"1.0"},"canonical_sha256":"49b23eaf794262ca5dada7ba768658a934124fa64f91f0d42b02c76fd44c7751","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:04.367835Z","signature_b64":"0fviZJN86zQSgE8pcishGkLxJNCPlf1L+rC3eIVZWvosf4nxVercHbzs1CV4crADaE/Zm7j7v8Z9U9znAWe4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49b23eaf794262ca5dada7ba768658a934124fa64f91f0d42b02c76fd44c7751","last_reissued_at":"2026-07-05T07:43:04.367426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:04.367426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05862","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":"2026-07-05T07:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SJ+InZrVHjiu/X4sZbM4WGaUQ0b62P1EmfduJnArqdGAOmPEVkUlzhFTgGS+it0T273Sxnk7QgPS0MVDSA1SDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:18:08.358346Z"},"content_sha256":"9f700f350c749b8384e515c34ada8cde57401f077972c3021c52dabae3a4f801","schema_version":"1.0","event_id":"sha256:9f700f350c749b8384e515c34ada8cde57401f077972c3021c52dabae3a4f801"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JGZD5L3ZIJRMUXNNU65HNBSYVE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anton Tsitsulin, Bahare Fatemi, Bryan Perozzi, Dustin Zelle, Jonathan Halcrow, Mehran Kazemi, Rami Al-Rfou","submitted_at":"2024-02-08T17:51:44Z","abstract_excerpt":"How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent structured data for LLMs. Our method, GraphToken, learns an encoding function to extend prompts with explicit structured information. Unlike other work which focuses on limited domains (e.g. knowledge graph representation), our work is the first effort focused on the general encoding of structured data to be used for various reasoning tasks. We show that explicitly representing the graph structure allows significant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05862","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/2402.05862/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":"2026-07-05T07:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdaIVo5VPa23Q2LZLsxq0YIJ/oCl9NZduhWBisIVzAxXCZGvSNcOvV+ABDj1uaMfyIUh5XejrXfd2Vn+7RGKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:18:08.359267Z"},"content_sha256":"5a3677117f5cc1cb7002edc5f4ad13f8ec12beda6bf20695dc77aa6054d6f79d","schema_version":"1.0","event_id":"sha256:5a3677117f5cc1cb7002edc5f4ad13f8ec12beda6bf20695dc77aa6054d6f79d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGZD5L3ZIJRMUXNNU65HNBSYVE/bundle.json","state_url":"https://pith.science/pith/JGZD5L3ZIJRMUXNNU65HNBSYVE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGZD5L3ZIJRMUXNNU65HNBSYVE/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":"2026-08-14T13:18:08Z","links":{"resolver":"https://pith.science/pith/JGZD5L3ZIJRMUXNNU65HNBSYVE","bundle":"https://pith.science/pith/JGZD5L3ZIJRMUXNNU65HNBSYVE/bundle.json","state":"https://pith.science/pith/JGZD5L3ZIJRMUXNNU65HNBSYVE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGZD5L3ZIJRMUXNNU65HNBSYVE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JGZD5L3ZIJRMUXNNU65HNBSYVE","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":"2a9fbaee99d4fb82efc0ac0e1684c86fe188c662c38e15056b3449a9c7a01121","cross_cats_sorted":["cs.AI","cs.SI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T17:51:44Z","title_canon_sha256":"40df187f5a3f87e954e9ebe819422fb9594b1c5f46e7730838d9554c55e696eb"},"schema_version":"1.0","source":{"id":"2402.05862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05862","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05862v1","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05862","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"JGZD5L3ZIJRM","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_16","alias_value":"JGZD5L3ZIJRMUXNN","created_at":"2026-07-05T07:43:04Z"},{"alias_kind":"pith_short_8","alias_value":"JGZD5L3Z","created_at":"2026-07-05T07:43:04Z"}],"graph_snapshots":[{"event_id":"sha256:5a3677117f5cc1cb7002edc5f4ad13f8ec12beda6bf20695dc77aa6054d6f79d","target":"graph","created_at":"2026-07-05T07:43:04Z","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/2402.05862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent structured data for LLMs. Our method, GraphToken, learns an encoding function to extend prompts with explicit structured information. Unlike other work which focuses on limited domains (e.g. knowledge graph representation), our work is the first effort focused on the general encoding of structured data to be used for various reasoning tasks. We show that explicitly representing the graph structure allows significant","authors_text":"Anton Tsitsulin, Bahare Fatemi, Bryan Perozzi, Dustin Zelle, Jonathan Halcrow, Mehran Kazemi, Rami Al-Rfou","cross_cats":["cs.AI","cs.SI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T17:51:44Z","title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05862","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":"sha256:9f700f350c749b8384e515c34ada8cde57401f077972c3021c52dabae3a4f801","target":"record","created_at":"2026-07-05T07:43:04Z","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":"2a9fbaee99d4fb82efc0ac0e1684c86fe188c662c38e15056b3449a9c7a01121","cross_cats_sorted":["cs.AI","cs.SI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T17:51:44Z","title_canon_sha256":"40df187f5a3f87e954e9ebe819422fb9594b1c5f46e7730838d9554c55e696eb"},"schema_version":"1.0","source":{"id":"2402.05862","kind":"arxiv","version":1}},"canonical_sha256":"49b23eaf794262ca5dada7ba768658a934124fa64f91f0d42b02c76fd44c7751","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49b23eaf794262ca5dada7ba768658a934124fa64f91f0d42b02c76fd44c7751","first_computed_at":"2026-07-05T07:43:04.367426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:04.367426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0fviZJN86zQSgE8pcishGkLxJNCPlf1L+rC3eIVZWvosf4nxVercHbzs1CV4crADaE/Zm7j7v8Z9U9znAWe4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:04.367835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f700f350c749b8384e515c34ada8cde57401f077972c3021c52dabae3a4f801","sha256:5a3677117f5cc1cb7002edc5f4ad13f8ec12beda6bf20695dc77aa6054d6f79d"],"state_sha256":"565f3e3a761bfbd48bafc6e1cb73b8f92f0398cbb353949b63d7826df27a9782"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jmZkYI0zDUMRR7qNKWgZ/nmr00eVFrzYfQFBAq3bmLoRdbL4glvg2AYcVgteUlUNQTDBrXncxzl6xoMQ+Uy4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:18:08.366419Z","bundle_sha256":"551abfb50c1d9f394b725e95361061a6c668fa861b23a6de0001048eaa95232b"}}