{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:REEG6KIGZKS7FT5OSFWFNFKI65","short_pith_number":"pith:REEG6KIG","schema_version":"1.0","canonical_sha256":"89086f2906caa5f2cfae916c569548f74dba7f65a0848fc28512a3980e2fc84b","source":{"kind":"arxiv","id":"2405.20684","version":2},"attestation_state":"computed","paper":{"title":"Joint Embeddings for Graph Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Aaron Haag, Oliver Lohse, Vlad Argatu","submitted_at":"2024-05-31T08:26:47Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive performance in text understanding and have become an essential tool for building smart assistants. Originally focusing on text, they have been enhanced with multimodal capabilities in recent works that successfully built visual instruction following assistants. As far as the graph modality goes, however, no such assistants have yet been developed. Graph structures are complex in that they represent relation between different features and are permutation invariant. Moreover, representing them in purely textual form does not always lead to go"},"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":"2405.20684","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-05-31T08:26:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f47a7a0eb27faf76123a5f59554bb54c8e0d1309006f6a66f25f8c5689dc073e","abstract_canon_sha256":"a0a787c7976e2a353bf563e497b586d7d7dbe0617b5b300bfdd46456c1c3e461"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:35.741323Z","signature_b64":"WYo87DMdSJjpKmj4xSwrrcpZuD9wOBQb0tpY522zEpBjBpiFTfrPlnuj/Nw09Fquaa4SBZcA1wwNWqDSCEf4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89086f2906caa5f2cfae916c569548f74dba7f65a0848fc28512a3980e2fc84b","last_reissued_at":"2026-07-05T09:24:35.740776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:35.740776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Embeddings for Graph Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Aaron Haag, Oliver Lohse, Vlad Argatu","submitted_at":"2024-05-31T08:26:47Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive performance in text understanding and have become an essential tool for building smart assistants. Originally focusing on text, they have been enhanced with multimodal capabilities in recent works that successfully built visual instruction following assistants. As far as the graph modality goes, however, no such assistants have yet been developed. Graph structures are complex in that they represent relation between different features and are permutation invariant. Moreover, representing them in purely textual form does not always lead to go"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20684","kind":"arxiv","version":2},"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/2405.20684/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":"2405.20684","created_at":"2026-07-05T09:24:35.740841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20684v2","created_at":"2026-07-05T09:24:35.740841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20684","created_at":"2026-07-05T09:24:35.740841+00:00"},{"alias_kind":"pith_short_12","alias_value":"REEG6KIGZKS7","created_at":"2026-07-05T09:24:35.740841+00:00"},{"alias_kind":"pith_short_16","alias_value":"REEG6KIGZKS7FT5O","created_at":"2026-07-05T09:24:35.740841+00:00"},{"alias_kind":"pith_short_8","alias_value":"REEG6KIG","created_at":"2026-07-05T09:24:35.740841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65","json":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65.json","graph_json":"https://pith.science/api/pith-number/REEG6KIGZKS7FT5OSFWFNFKI65/graph.json","events_json":"https://pith.science/api/pith-number/REEG6KIGZKS7FT5OSFWFNFKI65/events.json","paper":"https://pith.science/paper/REEG6KIG"},"agent_actions":{"view_html":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65","download_json":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65.json","view_paper":"https://pith.science/paper/REEG6KIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20684&json=true","fetch_graph":"https://pith.science/api/pith-number/REEG6KIGZKS7FT5OSFWFNFKI65/graph.json","fetch_events":"https://pith.science/api/pith-number/REEG6KIGZKS7FT5OSFWFNFKI65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65/action/storage_attestation","attest_author":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65/action/author_attestation","sign_citation":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65/action/citation_signature","submit_replication":"https://pith.science/pith/REEG6KIGZKS7FT5OSFWFNFKI65/action/replication_record"}},"created_at":"2026-07-05T09:24:35.740841+00:00","updated_at":"2026-07-05T09:24:35.740841+00:00"}