{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QZ3GYTFC6XONMQO237N4EBRCDI","short_pith_number":"pith:QZ3GYTFC","schema_version":"1.0","canonical_sha256":"86766c4ca2f5dcd641dadfdbc206221a2079be460f1860b33820558a2e9fd0eb","source":{"kind":"arxiv","id":"2407.21358","version":1},"attestation_state":"computed","paper":{"title":"Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anil Ramakrishna, Aram Galstyan, Charith Peris, Elan Markowitz, Jwala Dhamala, Kai-Wei Chang, Ninareh Mehrabi, Rahul Gupta","submitted_at":"2024-07-31T06:01:24Z","abstract_excerpt":"Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge. However, KGs and LLMs are often developed separately and must be integrated after training. We introduce Tree-of-Traversals, a novel zero-shot reasoning algorithm that enables augmentation of black-box LLMs with one or more KGs. The algorithm equips a LLM with actions for interfacing a KG and enables the LLM to perform tree search over possible thoughts and actions to find high confidence reasoning paths. We evaluate on two popular benchmark data"},"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":"2407.21358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-31T06:01:24Z","cross_cats_sorted":[],"title_canon_sha256":"ba5c1575fdcf7c0cfae7905a52a2123d1c738a7997ca1cd1de95f15b11a2c1dd","abstract_canon_sha256":"c5291d1a8ce63eed2bca4e17a782df678450e886699d9b15574a0aa6222a9dd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:38.078834Z","signature_b64":"+dEcSisDbd74Oq15NGmaw2zMOQmnC7nIpQvNeq3+HlzkIUkc1mGUwFmu1f+SifBLpCp8S3d9gwwNOBPr0pxiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86766c4ca2f5dcd641dadfdbc206221a2079be460f1860b33820558a2e9fd0eb","last_reissued_at":"2026-07-05T08:50:38.078418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:38.078418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anil Ramakrishna, Aram Galstyan, Charith Peris, Elan Markowitz, Jwala Dhamala, Kai-Wei Chang, Ninareh Mehrabi, Rahul Gupta","submitted_at":"2024-07-31T06:01:24Z","abstract_excerpt":"Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge. However, KGs and LLMs are often developed separately and must be integrated after training. We introduce Tree-of-Traversals, a novel zero-shot reasoning algorithm that enables augmentation of black-box LLMs with one or more KGs. The algorithm equips a LLM with actions for interfacing a KG and enables the LLM to perform tree search over possible thoughts and actions to find high confidence reasoning paths. We evaluate on two popular benchmark data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21358","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/2407.21358/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":"2407.21358","created_at":"2026-07-05T08:50:38.078478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21358v1","created_at":"2026-07-05T08:50:38.078478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21358","created_at":"2026-07-05T08:50:38.078478+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZ3GYTFC6XON","created_at":"2026-07-05T08:50:38.078478+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZ3GYTFC6XONMQO2","created_at":"2026-07-05T08:50:38.078478+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZ3GYTFC","created_at":"2026-07-05T08:50:38.078478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI","json":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI.json","graph_json":"https://pith.science/api/pith-number/QZ3GYTFC6XONMQO237N4EBRCDI/graph.json","events_json":"https://pith.science/api/pith-number/QZ3GYTFC6XONMQO237N4EBRCDI/events.json","paper":"https://pith.science/paper/QZ3GYTFC"},"agent_actions":{"view_html":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI","download_json":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI.json","view_paper":"https://pith.science/paper/QZ3GYTFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21358&json=true","fetch_graph":"https://pith.science/api/pith-number/QZ3GYTFC6XONMQO237N4EBRCDI/graph.json","fetch_events":"https://pith.science/api/pith-number/QZ3GYTFC6XONMQO237N4EBRCDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI/action/storage_attestation","attest_author":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI/action/author_attestation","sign_citation":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI/action/citation_signature","submit_replication":"https://pith.science/pith/QZ3GYTFC6XONMQO237N4EBRCDI/action/replication_record"}},"created_at":"2026-07-05T08:50:38.078478+00:00","updated_at":"2026-07-05T08:50:38.078478+00:00"}