{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2WFO6RG2RI533TFAYVJHGZKRPE","short_pith_number":"pith:2WFO6RG2","schema_version":"1.0","canonical_sha256":"d58aef44da8a3bbdcca0c552736551793a855caa511bc1f5150f87ef9b368688","source":{"kind":"arxiv","id":"2606.03705","version":1},"attestation_state":"computed","paper":{"title":"Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Wang, Jiafeng Guo, Jin Zhang, Kun Su, Long Bai, Weiwei Ding, Xiaolong Jin, Xueqi Cheng, Zhuo Chen, Zixuan Li","submitted_at":"2026-06-02T14:22:29Z","abstract_excerpt":"Knowledge Graphs (KGs) are widely used to mitigate the limitations of Large Language Models (LLMs), such as outdated knowledge and hallucinations. Existing LLM-KG integration frameworks typically rely on predefined operators to retrieve factual knowledge from KGs and inject it into prompts for answer generation. This paradigm faces two critical bottlenecks: 1) Inflexibility: The predefined operators are limited in scope and thus lack sufficient compositional expressiveness to fully capture the complex semantics required by KG questions. 2) Unscalability: Direct injection of factual knowledge i"},"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":"2606.03705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T14:22:29Z","cross_cats_sorted":[],"title_canon_sha256":"2bfbed0150493adc1a422311c4915d1e1b9cd9e6d4b7d5b8b6f9ffbe7bca36a0","abstract_canon_sha256":"48069fcdfa6121cd725f843cb067b315db1e7724c7bb1e7f9448c266f3eb5a65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:06:05.035171Z","signature_b64":"IPGhn5cQR/Bw+35E3KWV2I17R4wGV/gsKR4ZBhgcXzsZ1pRJhw8dv2HroSkPeCFMghBShPg5fgETVUlSBovlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d58aef44da8a3bbdcca0c552736551793a855caa511bc1f5150f87ef9b368688","last_reissued_at":"2026-06-03T01:06:05.034559Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:06:05.034559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Wang, Jiafeng Guo, Jin Zhang, Kun Su, Long Bai, Weiwei Ding, Xiaolong Jin, Xueqi Cheng, Zhuo Chen, Zixuan Li","submitted_at":"2026-06-02T14:22:29Z","abstract_excerpt":"Knowledge Graphs (KGs) are widely used to mitigate the limitations of Large Language Models (LLMs), such as outdated knowledge and hallucinations. Existing LLM-KG integration frameworks typically rely on predefined operators to retrieve factual knowledge from KGs and inject it into prompts for answer generation. This paradigm faces two critical bottlenecks: 1) Inflexibility: The predefined operators are limited in scope and thus lack sufficient compositional expressiveness to fully capture the complex semantics required by KG questions. 2) Unscalability: Direct injection of factual knowledge i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03705","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/2606.03705/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":"2606.03705","created_at":"2026-06-03T01:06:05.034662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03705v1","created_at":"2026-06-03T01:06:05.034662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03705","created_at":"2026-06-03T01:06:05.034662+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WFO6RG2RI53","created_at":"2026-06-03T01:06:05.034662+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WFO6RG2RI533TFA","created_at":"2026-06-03T01:06:05.034662+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WFO6RG2","created_at":"2026-06-03T01:06:05.034662+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/2WFO6RG2RI533TFAYVJHGZKRPE","json":"https://pith.science/pith/2WFO6RG2RI533TFAYVJHGZKRPE.json","graph_json":"https://pith.science/api/pith-number/2WFO6RG2RI533TFAYVJHGZKRPE/graph.json","events_json":"https://pith.science/api/pith-number/2WFO6RG2RI533TFAYVJHGZKRPE/events.json","paper":"https://pith.science/paper/2WFO6RG2"},"agent_actions":{"view_html":"https://pith.science/pith/2WFO6RG2RI533TFAYVJHGZKRPE","download_json":"https://pith.science/pith/2WFO6RG2RI533TFAYVJHGZKRPE.json","view_paper":"https://pith.science/paper/2WFO6RG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03705&json=true","fetch_graph":"https://pith.science/api/pith-number/2WFO6RG2RI533TFAYVJHGZKRPE/graph.json","fetch_events":"https://pith.science/api/pith-number/2WFO6RG2RI533TFAYVJHGZKRPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WFO6RG2RI533TFAYVJHGZKRPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WFO6RG2RI533TFAYVJHGZKRPE/action/storage_attestation","attest_author":"https://pith.science/pith/2WFO6RG2RI533TFAYVJHGZKRPE/action/author_attestation","sign_citation":"https://pith.science/pith/2WFO6RG2RI533TFAYVJHGZKRPE/action/citation_signature","submit_replication":"https://pith.science/pith/2WFO6RG2RI533TFAYVJHGZKRPE/action/replication_record"}},"created_at":"2026-06-03T01:06:05.034662+00:00","updated_at":"2026-06-03T01:06:05.034662+00:00"}