{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UH342JTCIH2Y5XJDDQWIGCUMHV","short_pith_number":"pith:UH342JTC","schema_version":"1.0","canonical_sha256":"a1f7cd266241f58edd231c2c830a8c3d744bdefe5333a3fd552fa49b056d7330","source":{"kind":"arxiv","id":"2608.06811","version":1},"attestation_state":"computed","paper":{"title":"Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jiahao Zhang, Yifan Zhang, Yu Huang","submitted_at":"2026-08-07T05:05:05Z","abstract_excerpt":"Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation, and verification. Success depends on both the base model's local reasoning and the agent's ability to maintain an evolving plan and remember observations across phases. Existing repository-level agents typically strengthen planning or memory in isolation, leaving long trajectories vulnerable to stale evidence, repeated failed edits, and verification inferred from the agent's own claims instead of execution evidence. "},"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":"2608.06811","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-07T05:05:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fffba98ab2ad76c7416e8d99d8d1697252b4e8c4cf91aa415b2bd7a599daaf67","abstract_canon_sha256":"0f2d42dac5ce6e449d1ccccccde7e6de81c1b327f3fc2e37ba33e51461bf56d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:12:09.941975Z","signature_b64":"/5Xvkd1iuiXxT5E/8wdel1+kyyZoTBU7U4wFucxfBgPrMYWoEP9zYLRpv+TrwMoCy8Cn/fQsIYDv9qACj43xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1f7cd266241f58edd231c2c830a8c3d744bdefe5333a3fd552fa49b056d7330","last_reissued_at":"2026-08-10T01:12:09.939054Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:12:09.939054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jiahao Zhang, Yifan Zhang, Yu Huang","submitted_at":"2026-08-07T05:05:05Z","abstract_excerpt":"Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation, and verification. Success depends on both the base model's local reasoning and the agent's ability to maintain an evolving plan and remember observations across phases. Existing repository-level agents typically strengthen planning or memory in isolation, leaving long trajectories vulnerable to stale evidence, repeated failed edits, and verification inferred from the agent's own claims instead of execution evidence. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06811","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/2608.06811/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":"2608.06811","created_at":"2026-08-10T01:12:09.940529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06811v1","created_at":"2026-08-10T01:12:09.940529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06811","created_at":"2026-08-10T01:12:09.940529+00:00"},{"alias_kind":"pith_short_12","alias_value":"UH342JTCIH2Y","created_at":"2026-08-10T01:12:09.940529+00:00"},{"alias_kind":"pith_short_16","alias_value":"UH342JTCIH2Y5XJD","created_at":"2026-08-10T01:12:09.940529+00:00"},{"alias_kind":"pith_short_8","alias_value":"UH342JTC","created_at":"2026-08-10T01:12:09.940529+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/UH342JTCIH2Y5XJDDQWIGCUMHV","json":"https://pith.science/pith/UH342JTCIH2Y5XJDDQWIGCUMHV.json","graph_json":"https://pith.science/api/pith-number/UH342JTCIH2Y5XJDDQWIGCUMHV/graph.json","events_json":"https://pith.science/api/pith-number/UH342JTCIH2Y5XJDDQWIGCUMHV/events.json","paper":"https://pith.science/paper/UH342JTC"},"agent_actions":{"view_html":"https://pith.science/pith/UH342JTCIH2Y5XJDDQWIGCUMHV","download_json":"https://pith.science/pith/UH342JTCIH2Y5XJDDQWIGCUMHV.json","view_paper":"https://pith.science/paper/UH342JTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06811&json=true","fetch_graph":"https://pith.science/api/pith-number/UH342JTCIH2Y5XJDDQWIGCUMHV/graph.json","fetch_events":"https://pith.science/api/pith-number/UH342JTCIH2Y5XJDDQWIGCUMHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UH342JTCIH2Y5XJDDQWIGCUMHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UH342JTCIH2Y5XJDDQWIGCUMHV/action/storage_attestation","attest_author":"https://pith.science/pith/UH342JTCIH2Y5XJDDQWIGCUMHV/action/author_attestation","sign_citation":"https://pith.science/pith/UH342JTCIH2Y5XJDDQWIGCUMHV/action/citation_signature","submit_replication":"https://pith.science/pith/UH342JTCIH2Y5XJDDQWIGCUMHV/action/replication_record"}},"created_at":"2026-08-10T01:12:09.940529+00:00","updated_at":"2026-08-10T01:12:09.940529+00:00"}