{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J4M3EPWM6CR53WRQ4LK6UKSO3E","short_pith_number":"pith:J4M3EPWM","schema_version":"1.0","canonical_sha256":"4f19b23eccf0a3ddda30e2d5ea2a4ed9380f0e6de114c31535e3a6e48e05eb83","source":{"kind":"arxiv","id":"2607.28126","version":1},"attestation_state":"computed","paper":{"title":"ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingchen Liu, Guangyuan Dong, Lei Liu, Shuyue Wei, Xiangtian Meng, Xing Fu, Xin Li, Yuanyuan Fang, Yuanyuan Gao","submitted_at":"2026-07-30T12:35:06Z","abstract_excerpt":"Long-horizon steel-equipment inspection requires reasoning over heterogeneous records accumulated across repeated inspection cycles. Existing retrieval-augmented generation systems treat historical logs as a static corpus and retain records without estimating their diagnostic value, failing to report early risk. To this end, we propose ConMem, a contribution-aware memory framework for LLM-assisted equipment inspection, supporting a human-in-the-loop early-risk screening system. Specifically, our ConMem first segments inspection logs into functional evidence units, then estimates each memory un"},"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":"2607.28126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T12:35:06Z","cross_cats_sorted":[],"title_canon_sha256":"ac1948cb0ced799acdc511da1c587bbe7d1e1eb22bc63b55ff702704968e7d83","abstract_canon_sha256":"00b09bdbf71c7e3b7023cd2a4f14e920127356dfad663a7edbef90103f000b31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f19b23eccf0a3ddda30e2d5ea2a4ed9380f0e6de114c31535e3a6e48e05eb83","last_reissued_at":"2026-07-31T01:35:49.571920Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:49.571920Z"},"graph_snapshot":{"paper":{"title":"ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingchen Liu, Guangyuan Dong, Lei Liu, Shuyue Wei, Xiangtian Meng, Xing Fu, Xin Li, Yuanyuan Fang, Yuanyuan Gao","submitted_at":"2026-07-30T12:35:06Z","abstract_excerpt":"Long-horizon steel-equipment inspection requires reasoning over heterogeneous records accumulated across repeated inspection cycles. Existing retrieval-augmented generation systems treat historical logs as a static corpus and retain records without estimating their diagnostic value, failing to report early risk. To this end, we propose ConMem, a contribution-aware memory framework for LLM-assisted equipment inspection, supporting a human-in-the-loop early-risk screening system. Specifically, our ConMem first segments inspection logs into functional evidence units, then estimates each memory un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28126","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/2607.28126/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":"2607.28126","created_at":"2026-07-31T01:35:49.575050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28126v1","created_at":"2026-07-31T01:35:49.575050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28126","created_at":"2026-07-31T01:35:49.575050+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4M3EPWM6CR5","created_at":"2026-07-31T01:35:49.575050+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4M3EPWM6CR53WRQ","created_at":"2026-07-31T01:35:49.575050+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4M3EPWM","created_at":"2026-07-31T01:35:49.575050+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/J4M3EPWM6CR53WRQ4LK6UKSO3E","json":"https://pith.science/pith/J4M3EPWM6CR53WRQ4LK6UKSO3E.json","graph_json":"https://pith.science/api/pith-number/J4M3EPWM6CR53WRQ4LK6UKSO3E/graph.json","events_json":"https://pith.science/api/pith-number/J4M3EPWM6CR53WRQ4LK6UKSO3E/events.json","paper":"https://pith.science/paper/J4M3EPWM"},"agent_actions":{"view_html":"https://pith.science/pith/J4M3EPWM6CR53WRQ4LK6UKSO3E","download_json":"https://pith.science/pith/J4M3EPWM6CR53WRQ4LK6UKSO3E.json","view_paper":"https://pith.science/paper/J4M3EPWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28126&json=true","fetch_graph":"https://pith.science/api/pith-number/J4M3EPWM6CR53WRQ4LK6UKSO3E/graph.json","fetch_events":"https://pith.science/api/pith-number/J4M3EPWM6CR53WRQ4LK6UKSO3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4M3EPWM6CR53WRQ4LK6UKSO3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4M3EPWM6CR53WRQ4LK6UKSO3E/action/storage_attestation","attest_author":"https://pith.science/pith/J4M3EPWM6CR53WRQ4LK6UKSO3E/action/author_attestation","sign_citation":"https://pith.science/pith/J4M3EPWM6CR53WRQ4LK6UKSO3E/action/citation_signature","submit_replication":"https://pith.science/pith/J4M3EPWM6CR53WRQ4LK6UKSO3E/action/replication_record"}},"created_at":"2026-07-31T01:35:49.575050+00:00","updated_at":"2026-07-31T01:35:49.575050+00:00"}