{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:APQR6EC6QP2KYS7YNVW3LFCCLQ","short_pith_number":"pith:APQR6EC6","schema_version":"1.0","canonical_sha256":"03e11f105e83f4ac4bf86d6db594425c0ab2f7bc5105e187f56f0d1f826dae1d","source":{"kind":"arxiv","id":"2606.28338","version":1},"attestation_state":"computed","paper":{"title":"Memory Shot for Long-Term Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chunyi Peng, Ge Yu, Haidong Xin, Shuo Wang, Xin Dai, Xuanshuo Sheng, Yu Gu, Yukun Yan, Zhenghao Liu, Zulong Chen","submitted_at":"2026-05-30T01:59:52Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong capabilities in general conversation, instruction following, and complex reasoning. However, in long-term dialogue settings, they often struggle to locate and utilize historical information most relevant to the current query. Existing approaches address this issue by constructing structured text-centered memory units through compressing and reorganizing user interaction history. However, these systems often rely on brute-force extraction of crucial evidence to associate episodes across dialogue sessions, causing substantial computational ov"},"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":"2606.28338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-30T01:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"65563ae6c53fe715ad9c7811cde38f8052cc1acd5df6bd8f28081c8ac98838cd","abstract_canon_sha256":"30f3746cbb7185a6abf176eeaedc8425f8aa482a73b808f4fde30d5e63dafbbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:11.297105Z","signature_b64":"FHGdTvw3g2kuUV1OyjVZFFXyr6LWGGJJsjIIMQhX3G6Wx1a7FPq0r641c1Rlv3MDmhTnlvgGs1xCoaiVr7vqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03e11f105e83f4ac4bf86d6db594425c0ab2f7bc5105e187f56f0d1f826dae1d","last_reissued_at":"2026-06-30T00:15:11.296184Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:11.296184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Shot for Long-Term Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chunyi Peng, Ge Yu, Haidong Xin, Shuo Wang, Xin Dai, Xuanshuo Sheng, Yu Gu, Yukun Yan, Zhenghao Liu, Zulong Chen","submitted_at":"2026-05-30T01:59:52Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong capabilities in general conversation, instruction following, and complex reasoning. However, in long-term dialogue settings, they often struggle to locate and utilize historical information most relevant to the current query. Existing approaches address this issue by constructing structured text-centered memory units through compressing and reorganizing user interaction history. However, these systems often rely on brute-force extraction of crucial evidence to associate episodes across dialogue sessions, causing substantial computational ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28338","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/2606.28338/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":"2606.28338","created_at":"2026-06-30T00:15:11.296693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28338v1","created_at":"2026-06-30T00:15:11.296693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28338","created_at":"2026-06-30T00:15:11.296693+00:00"},{"alias_kind":"pith_short_12","alias_value":"APQR6EC6QP2K","created_at":"2026-06-30T00:15:11.296693+00:00"},{"alias_kind":"pith_short_16","alias_value":"APQR6EC6QP2KYS7Y","created_at":"2026-06-30T00:15:11.296693+00:00"},{"alias_kind":"pith_short_8","alias_value":"APQR6EC6","created_at":"2026-06-30T00:15:11.296693+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/APQR6EC6QP2KYS7YNVW3LFCCLQ","json":"https://pith.science/pith/APQR6EC6QP2KYS7YNVW3LFCCLQ.json","graph_json":"https://pith.science/api/pith-number/APQR6EC6QP2KYS7YNVW3LFCCLQ/graph.json","events_json":"https://pith.science/api/pith-number/APQR6EC6QP2KYS7YNVW3LFCCLQ/events.json","paper":"https://pith.science/paper/APQR6EC6"},"agent_actions":{"view_html":"https://pith.science/pith/APQR6EC6QP2KYS7YNVW3LFCCLQ","download_json":"https://pith.science/pith/APQR6EC6QP2KYS7YNVW3LFCCLQ.json","view_paper":"https://pith.science/paper/APQR6EC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28338&json=true","fetch_graph":"https://pith.science/api/pith-number/APQR6EC6QP2KYS7YNVW3LFCCLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/APQR6EC6QP2KYS7YNVW3LFCCLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APQR6EC6QP2KYS7YNVW3LFCCLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APQR6EC6QP2KYS7YNVW3LFCCLQ/action/storage_attestation","attest_author":"https://pith.science/pith/APQR6EC6QP2KYS7YNVW3LFCCLQ/action/author_attestation","sign_citation":"https://pith.science/pith/APQR6EC6QP2KYS7YNVW3LFCCLQ/action/citation_signature","submit_replication":"https://pith.science/pith/APQR6EC6QP2KYS7YNVW3LFCCLQ/action/replication_record"}},"created_at":"2026-06-30T00:15:11.296693+00:00","updated_at":"2026-06-30T00:15:11.296693+00:00"}