{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I372GF3WMLKZ3VFTS3ZXKD4NWT","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":"9d6278e5c0fb1c204e365638de18396babbf50a030dc1c9185e54cb7da0ce5ca","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T14:33:24Z","title_canon_sha256":"d8135ffb2003fa1c8cf68d17990aeed320b973eb3e4c10f2e8a3cf706490ec39"},"schema_version":"1.0","source":{"id":"2402.12177","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12177","created_at":"2026-07-05T07:55:14Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12177v4","created_at":"2026-07-05T07:55:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12177","created_at":"2026-07-05T07:55:14Z"},{"alias_kind":"pith_short_12","alias_value":"I372GF3WMLKZ","created_at":"2026-07-05T07:55:14Z"},{"alias_kind":"pith_short_16","alias_value":"I372GF3WMLKZ3VFT","created_at":"2026-07-05T07:55:14Z"},{"alias_kind":"pith_short_8","alias_value":"I372GF3W","created_at":"2026-07-05T07:55:14Z"}],"graph_snapshots":[{"event_id":"sha256:a9880edf206a68d67731ec32b7e14293b8377a7839c2b844512ce54af9180818","target":"graph","created_at":"2026-07-05T07:55:14Z","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/2402.12177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval Augmented Generation (RAG) has emerged as an effective solution for mitigating hallucinations in Large Language Models (LLMs). The retrieval stage in RAG typically involves a pre-trained embedding model, which converts queries and passages into vectors to capture their semantics. However, a standard pre-trained embedding model may exhibit sub-optimal performance when applied to specific domain knowledge, necessitating fine-tuning. This paper addresses scenarios where the embeddings are only available from a black-box model. We introduce Model augmented fine-tuning (Mafin) -- a novel ","authors_text":"David Barber, Mingtian Zhang, Peter Hayes, Shawn Lan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T14:33:24Z","title":"Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12177","kind":"arxiv","version":4},"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:c7675a813f37c20e2c8c35f0ef4b9a3a926d30f68afc365dd14b6128c161bd91","target":"record","created_at":"2026-07-05T07:55:14Z","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":"9d6278e5c0fb1c204e365638de18396babbf50a030dc1c9185e54cb7da0ce5ca","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T14:33:24Z","title_canon_sha256":"d8135ffb2003fa1c8cf68d17990aeed320b973eb3e4c10f2e8a3cf706490ec39"},"schema_version":"1.0","source":{"id":"2402.12177","kind":"arxiv","version":4}},"canonical_sha256":"46ffa3177662d59dd4b396f3750f8db4c02cd77964bdab87b531fd8bb6d663c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46ffa3177662d59dd4b396f3750f8db4c02cd77964bdab87b531fd8bb6d663c1","first_computed_at":"2026-07-05T07:55:14.360269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:14.360269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HKgtl66TNpAv1VyeyCDotMePYdHZgkkzVGAwOt6LpIndMGOGRv4bgL35XT/RmPHC1NtCTx7au8zXDg5vVx58Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:14.360740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12177","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7675a813f37c20e2c8c35f0ef4b9a3a926d30f68afc365dd14b6128c161bd91","sha256:a9880edf206a68d67731ec32b7e14293b8377a7839c2b844512ce54af9180818"],"state_sha256":"3e72b819b60e89e269cf69223b1e4ec3b67dd5bfa1285cff7b13728ffb18dd01"}