{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7VS7JEC43X354NPEIDXVGFCVMU","short_pith_number":"pith:7VS7JEC4","schema_version":"1.0","canonical_sha256":"fd65f4905cddf7de35e440ef5314556531277661521997b7a6817ddc0d82d448","source":{"kind":"arxiv","id":"2606.07711","version":1},"attestation_state":"computed","paper":{"title":"Rosetta Memory: Adaptive Memory for Cross-LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoxuan Li, Hao Yang, Shiqi Shen, Xu Chen, Zhi Gong, Zhipeng Wang","submitted_at":"2026-06-05T13:50:59Z","abstract_excerpt":"Memory is the key component for transforming a stateless LLM into a persistent, evolving agent through experience accumulation, long-horizon planning, and continual self-improvement. Existing memory systems typically take the LLM as the center and design memory operations tailored to a specific backbone. In practice, however, users frequently switch between LLMs, for example using Claude for coding and GPT for writing across tasks, or routing different steps to different backbones within a single task for cost-effective trade-offs. As a result, memory written by one model often needs to be con"},"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":"2606.07711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T13:50:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df9c32850f218763055254d2a54c77a18f72629f598a95133d996b64f731d1ba","abstract_canon_sha256":"08f704f1f089d500e885fd6f2922eb4f2790a3a9e1405b04eb23a162ac0a717d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:49.979431Z","signature_b64":"yMRq0m5r8bwZ+8ztbu6OdHCUBUpq+5XIjuEpHlx3AXSx2j9bvU4vT71gOZ71SvNH3nngYw0AG1HWipRvSJnfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd65f4905cddf7de35e440ef5314556531277661521997b7a6817ddc0d82d448","last_reissued_at":"2026-06-09T01:04:49.979028Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:49.979028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rosetta Memory: Adaptive Memory for Cross-LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoxuan Li, Hao Yang, Shiqi Shen, Xu Chen, Zhi Gong, Zhipeng Wang","submitted_at":"2026-06-05T13:50:59Z","abstract_excerpt":"Memory is the key component for transforming a stateless LLM into a persistent, evolving agent through experience accumulation, long-horizon planning, and continual self-improvement. Existing memory systems typically take the LLM as the center and design memory operations tailored to a specific backbone. In practice, however, users frequently switch between LLMs, for example using Claude for coding and GPT for writing across tasks, or routing different steps to different backbones within a single task for cost-effective trade-offs. As a result, memory written by one model often needs to be con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07711","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/2606.07711/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":"2606.07711","created_at":"2026-06-09T01:04:49.979083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07711v1","created_at":"2026-06-09T01:04:49.979083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07711","created_at":"2026-06-09T01:04:49.979083+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VS7JEC43X35","created_at":"2026-06-09T01:04:49.979083+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VS7JEC43X354NPE","created_at":"2026-06-09T01:04:49.979083+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VS7JEC4","created_at":"2026-06-09T01:04:49.979083+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/7VS7JEC43X354NPEIDXVGFCVMU","json":"https://pith.science/pith/7VS7JEC43X354NPEIDXVGFCVMU.json","graph_json":"https://pith.science/api/pith-number/7VS7JEC43X354NPEIDXVGFCVMU/graph.json","events_json":"https://pith.science/api/pith-number/7VS7JEC43X354NPEIDXVGFCVMU/events.json","paper":"https://pith.science/paper/7VS7JEC4"},"agent_actions":{"view_html":"https://pith.science/pith/7VS7JEC43X354NPEIDXVGFCVMU","download_json":"https://pith.science/pith/7VS7JEC43X354NPEIDXVGFCVMU.json","view_paper":"https://pith.science/paper/7VS7JEC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07711&json=true","fetch_graph":"https://pith.science/api/pith-number/7VS7JEC43X354NPEIDXVGFCVMU/graph.json","fetch_events":"https://pith.science/api/pith-number/7VS7JEC43X354NPEIDXVGFCVMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VS7JEC43X354NPEIDXVGFCVMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VS7JEC43X354NPEIDXVGFCVMU/action/storage_attestation","attest_author":"https://pith.science/pith/7VS7JEC43X354NPEIDXVGFCVMU/action/author_attestation","sign_citation":"https://pith.science/pith/7VS7JEC43X354NPEIDXVGFCVMU/action/citation_signature","submit_replication":"https://pith.science/pith/7VS7JEC43X354NPEIDXVGFCVMU/action/replication_record"}},"created_at":"2026-06-09T01:04:49.979083+00:00","updated_at":"2026-06-09T01:04:49.979083+00:00"}