{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PVMCOXLC32ZUSKF5FRXXTLOV4E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dfc6d1d34d7be68b6559c31cce26139bcb277b36d56c818f3af13e26ef7ff18c","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T13:03:49Z","title_canon_sha256":"cee6a07f5d3f7fa7d1e8346984311c4b4cee11f143b34e1faa5f90efac09e770"},"schema_version":"1.0","source":{"id":"2608.13200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13200","created_at":"2026-08-14T01:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13200v1","created_at":"2026-08-14T01:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13200","created_at":"2026-08-14T01:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"PVMCOXLC32ZU","created_at":"2026-08-14T01:00:39Z"},{"alias_kind":"pith_short_16","alias_value":"PVMCOXLC32ZUSKF5","created_at":"2026-08-14T01:00:39Z"},{"alias_kind":"pith_short_8","alias_value":"PVMCOXLC","created_at":"2026-08-14T01:00:39Z"}],"graph_snapshots":[{"event_id":"sha256:0bf6b19752f73f1c788fbc8e137bcb82dc7f4fffe8567b1385141d9254028f95","target":"graph","created_at":"2026-08-14T01:00:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.13200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern LLMs excel at reasoning and instruction following, enabling users to express complex and diverse information needs. However, conventional retrievers largely rely on surface-level matching between queries and documents, resulting in a growing gap between how users express their needs and how retrievers interpret them. In this paper, we present GEM, a generative embedding model that augments retrieval through its own knowledge by explicitly reasoning about user intent and relevance criteria. GEM unifies generation and embedding within a single model: it first reasons over the query, then ","authors_text":"Craig Macdonald, Zhili Shen","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T13:03:49Z","title":"GEM: A Generative Embedding Model Bridging Reasoning and Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13200","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e76938d5e56bdf1b03d9ca439176bde47c069771ca65c88a6b0a50db0d71062b","target":"record","created_at":"2026-08-14T01:00:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dfc6d1d34d7be68b6559c31cce26139bcb277b36d56c818f3af13e26ef7ff18c","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T13:03:49Z","title_canon_sha256":"cee6a07f5d3f7fa7d1e8346984311c4b4cee11f143b34e1faa5f90efac09e770"},"schema_version":"1.0","source":{"id":"2608.13200","kind":"arxiv","version":1}},"canonical_sha256":"7d58275d62deb34928bd2c6f79add5e12c516a4fd5c9f0dfe7793308f8532d94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d58275d62deb34928bd2c6f79add5e12c516a4fd5c9f0dfe7793308f8532d94","first_computed_at":"2026-08-14T01:00:39.050908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:39.050908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EzhWqw4ulgTJSUKfga/jb553+aHaaP+XkLdWwYI6DGZkYXYpdByn6iC+DRz6aHUF0u+EFoqzamABB8Z+IQFVAg==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:39.053028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e76938d5e56bdf1b03d9ca439176bde47c069771ca65c88a6b0a50db0d71062b","sha256:0bf6b19752f73f1c788fbc8e137bcb82dc7f4fffe8567b1385141d9254028f95"],"state_sha256":"90a88822dbffb2033f30498c7ab701cff7d9b58826ed91a90a806c66ddeafb12"}