{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZKUO2UY7HQMKYVKGN2WZS6LL5Q","short_pith_number":"pith:ZKUO2UY7","schema_version":"1.0","canonical_sha256":"caa8ed531f3c18ac55466ead99796bec1e7a092a6d35a790048ae599695e2e79","source":{"kind":"arxiv","id":"2607.21106","version":1},"attestation_state":"computed","paper":{"title":"AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongze Chen, Qinfeng Li, Wenqi Zhang, Xinyan Yu, Xuhong Zhang, Yuntai Bao","submitted_at":"2026-07-23T09:35:34Z","abstract_excerpt":"Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, compress, or discard as interactions accumulate. Heuristic memory methods rely on subjective, task-specific rules, which can misalign with downstream objectives and limit cross-task adaptability. RL-based methods, by contrast, learn from task feedback but mainly use outcome- or module-level rewards. These coarse signals indicate task success but cannot identify which intermediate memory contents support the final answe"},"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":"2607.21106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T09:35:34Z","cross_cats_sorted":[],"title_canon_sha256":"bd8a5192fe3656c08535f3c2f882c325eb267aa5550c186e0f425f4a04f72568","abstract_canon_sha256":"b85d3bdb14e3b08e20ef32dc3090b6140b8b67e51b30e5689d224d6229426134"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:52.217788Z","signature_b64":"xpMa83t6WIo44iuay2dNhytM4+oVYE1WbrmHv5px+aZdb91Symqb+USg6eRik6882SJxmN+7zps6CJJCWl3VCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa8ed531f3c18ac55466ead99796bec1e7a092a6d35a790048ae599695e2e79","last_reissued_at":"2026-07-24T01:23:52.216826Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:52.216826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongze Chen, Qinfeng Li, Wenqi Zhang, Xinyan Yu, Xuhong Zhang, Yuntai Bao","submitted_at":"2026-07-23T09:35:34Z","abstract_excerpt":"Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, compress, or discard as interactions accumulate. Heuristic memory methods rely on subjective, task-specific rules, which can misalign with downstream objectives and limit cross-task adaptability. RL-based methods, by contrast, learn from task feedback but mainly use outcome- or module-level rewards. These coarse signals indicate task success but cannot identify which intermediate memory contents support the final answe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21106","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/2607.21106/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":"2607.21106","created_at":"2026-07-24T01:23:52.217271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21106v1","created_at":"2026-07-24T01:23:52.217271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21106","created_at":"2026-07-24T01:23:52.217271+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKUO2UY7HQMK","created_at":"2026-07-24T01:23:52.217271+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKUO2UY7HQMKYVKG","created_at":"2026-07-24T01:23:52.217271+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKUO2UY7","created_at":"2026-07-24T01:23:52.217271+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/ZKUO2UY7HQMKYVKGN2WZS6LL5Q","json":"https://pith.science/pith/ZKUO2UY7HQMKYVKGN2WZS6LL5Q.json","graph_json":"https://pith.science/api/pith-number/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/graph.json","events_json":"https://pith.science/api/pith-number/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/events.json","paper":"https://pith.science/paper/ZKUO2UY7"},"agent_actions":{"view_html":"https://pith.science/pith/ZKUO2UY7HQMKYVKGN2WZS6LL5Q","download_json":"https://pith.science/pith/ZKUO2UY7HQMKYVKGN2WZS6LL5Q.json","view_paper":"https://pith.science/paper/ZKUO2UY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21106&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/action/storage_attestation","attest_author":"https://pith.science/pith/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/action/author_attestation","sign_citation":"https://pith.science/pith/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/action/citation_signature","submit_replication":"https://pith.science/pith/ZKUO2UY7HQMKYVKGN2WZS6LL5Q/action/replication_record"}},"created_at":"2026-07-24T01:23:52.217271+00:00","updated_at":"2026-07-24T01:23:52.217271+00:00"}