{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SPUXM4DP57ZBLEHDI6QCQ3KUTE","short_pith_number":"pith:SPUXM4DP","schema_version":"1.0","canonical_sha256":"93e976706feff21590e347a0286d5499184a7a4428e83e7f499972ed89725556","source":{"kind":"arxiv","id":"2606.03463","version":1},"attestation_state":"computed","paper":{"title":"DMF: A Deterministic Memory Framework for Conversational AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Enrico Zimuel, Matteo Stabile","submitted_at":"2026-06-02T10:41:28Z","abstract_excerpt":"Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons. Existing approaches rely predominantly on large language model (LLM)-based summarisation at write time, which introduces non-determinism, escalating token costs, and opacity in pruning decisions. We present the Deterministic Memory Framework (DMF), a CPU-first approach that replaces generative memory compression with a fully deterministic pipeline grounded in classical NLP analysis, vector geometry, and mathematical scoring. DMF assigns each conversational interact"},"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":"2606.03463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T10:41:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8481d876e6402fe0de88b5ccb5dacc21edc7a2e4ed5ede8665340f2ab96580b3","abstract_canon_sha256":"1d1d06a5844eca5c689b04022e1949c51849e607958e145c68fae07ec8bf9479"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:58.557374Z","signature_b64":"jwszkRw+flKhyyBP0Gv/+RTcswf9UGWpS9keThz6F4jnD9dRW7ObLH5j4uG65pi+rpGnppKFBGeOJhyNbTHkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93e976706feff21590e347a0286d5499184a7a4428e83e7f499972ed89725556","last_reissued_at":"2026-06-03T01:05:58.557025Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:58.557025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DMF: A Deterministic Memory Framework for Conversational AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Enrico Zimuel, Matteo Stabile","submitted_at":"2026-06-02T10:41:28Z","abstract_excerpt":"Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons. Existing approaches rely predominantly on large language model (LLM)-based summarisation at write time, which introduces non-determinism, escalating token costs, and opacity in pruning decisions. We present the Deterministic Memory Framework (DMF), a CPU-first approach that replaces generative memory compression with a fully deterministic pipeline grounded in classical NLP analysis, vector geometry, and mathematical scoring. DMF assigns each conversational interact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03463","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/2606.03463/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":"2606.03463","created_at":"2026-06-03T01:05:58.557080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03463v1","created_at":"2026-06-03T01:05:58.557080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03463","created_at":"2026-06-03T01:05:58.557080+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPUXM4DP57ZB","created_at":"2026-06-03T01:05:58.557080+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPUXM4DP57ZBLEHD","created_at":"2026-06-03T01:05:58.557080+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPUXM4DP","created_at":"2026-06-03T01:05:58.557080+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/SPUXM4DP57ZBLEHDI6QCQ3KUTE","json":"https://pith.science/pith/SPUXM4DP57ZBLEHDI6QCQ3KUTE.json","graph_json":"https://pith.science/api/pith-number/SPUXM4DP57ZBLEHDI6QCQ3KUTE/graph.json","events_json":"https://pith.science/api/pith-number/SPUXM4DP57ZBLEHDI6QCQ3KUTE/events.json","paper":"https://pith.science/paper/SPUXM4DP"},"agent_actions":{"view_html":"https://pith.science/pith/SPUXM4DP57ZBLEHDI6QCQ3KUTE","download_json":"https://pith.science/pith/SPUXM4DP57ZBLEHDI6QCQ3KUTE.json","view_paper":"https://pith.science/paper/SPUXM4DP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03463&json=true","fetch_graph":"https://pith.science/api/pith-number/SPUXM4DP57ZBLEHDI6QCQ3KUTE/graph.json","fetch_events":"https://pith.science/api/pith-number/SPUXM4DP57ZBLEHDI6QCQ3KUTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPUXM4DP57ZBLEHDI6QCQ3KUTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPUXM4DP57ZBLEHDI6QCQ3KUTE/action/storage_attestation","attest_author":"https://pith.science/pith/SPUXM4DP57ZBLEHDI6QCQ3KUTE/action/author_attestation","sign_citation":"https://pith.science/pith/SPUXM4DP57ZBLEHDI6QCQ3KUTE/action/citation_signature","submit_replication":"https://pith.science/pith/SPUXM4DP57ZBLEHDI6QCQ3KUTE/action/replication_record"}},"created_at":"2026-06-03T01:05:58.557080+00:00","updated_at":"2026-06-03T01:05:58.557080+00:00"}