{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YMOGC5O2ZTHGFWDW2CAGU67JN7","short_pith_number":"pith:YMOGC5O2","schema_version":"1.0","canonical_sha256":"c31c6175daccce62d876d0806a7be96fed0a4019e62781ba57c34d8fb32e22e6","source":{"kind":"arxiv","id":"2504.09283","version":1},"attestation_state":"computed","paper":{"title":"Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Amine Mhedhbi, Daniel Lee, Elena L. Glassman, Frida-Cecilia Acosta-Parenteau, Ian Arawjo, Munyeong Kim, Priyan Vaithilingam","submitted_at":"2025-04-12T17:07:08Z","abstract_excerpt":"How do we update AI memory of user intent as intent changes? We consider how an AI interface may assist the integration of new information into a repository of natural language data. Inspired by software engineering concepts like impact analysis, we develop methods and a UI for managing semantic changes with non-local effects, which we call \"semantic conflict resolution.\" The user commits new intent to a project -- makes a \"semantic commit\" -- and the AI helps the user detect and resolve semantic conflicts within a store of existing information representing their intent (an \"intent specificati"},"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":"2504.09283","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-04-12T17:07:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5fa2853e1ed1a82d3d11e409ca6309afea11fa68c46e19f0545e049735e3b94b","abstract_canon_sha256":"7175067f9488b41b8e6fcd4971bb8c712d71a704fb501445e543b6c2442eb411"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:34.418092Z","signature_b64":"f1FjFjwfH7ROekSRQR3JXCST+H199h3prMK6/J6XvtAnbdgyumPSC0fII5MZ8y0T5vL3BtOf3egA9MhtR0LGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c31c6175daccce62d876d0806a7be96fed0a4019e62781ba57c34d8fb32e22e6","last_reissued_at":"2026-07-05T10:48:34.417619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:34.417619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Amine Mhedhbi, Daniel Lee, Elena L. Glassman, Frida-Cecilia Acosta-Parenteau, Ian Arawjo, Munyeong Kim, Priyan Vaithilingam","submitted_at":"2025-04-12T17:07:08Z","abstract_excerpt":"How do we update AI memory of user intent as intent changes? We consider how an AI interface may assist the integration of new information into a repository of natural language data. Inspired by software engineering concepts like impact analysis, we develop methods and a UI for managing semantic changes with non-local effects, which we call \"semantic conflict resolution.\" The user commits new intent to a project -- makes a \"semantic commit\" -- and the AI helps the user detect and resolve semantic conflicts within a store of existing information representing their intent (an \"intent specificati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09283","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/2504.09283/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":"2504.09283","created_at":"2026-07-05T10:48:34.417677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09283v1","created_at":"2026-07-05T10:48:34.417677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09283","created_at":"2026-07-05T10:48:34.417677+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMOGC5O2ZTHG","created_at":"2026-07-05T10:48:34.417677+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMOGC5O2ZTHGFWDW","created_at":"2026-07-05T10:48:34.417677+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMOGC5O2","created_at":"2026-07-05T10:48:34.417677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10587","citing_title":"CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning Tasks","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7","json":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7.json","graph_json":"https://pith.science/api/pith-number/YMOGC5O2ZTHGFWDW2CAGU67JN7/graph.json","events_json":"https://pith.science/api/pith-number/YMOGC5O2ZTHGFWDW2CAGU67JN7/events.json","paper":"https://pith.science/paper/YMOGC5O2"},"agent_actions":{"view_html":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7","download_json":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7.json","view_paper":"https://pith.science/paper/YMOGC5O2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09283&json=true","fetch_graph":"https://pith.science/api/pith-number/YMOGC5O2ZTHGFWDW2CAGU67JN7/graph.json","fetch_events":"https://pith.science/api/pith-number/YMOGC5O2ZTHGFWDW2CAGU67JN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7/action/storage_attestation","attest_author":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7/action/author_attestation","sign_citation":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7/action/citation_signature","submit_replication":"https://pith.science/pith/YMOGC5O2ZTHGFWDW2CAGU67JN7/action/replication_record"}},"created_at":"2026-07-05T10:48:34.417677+00:00","updated_at":"2026-07-05T10:48:34.417677+00:00"}