{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I372GF3WMLKZ3VFTS3ZXKD4NWT","short_pith_number":"pith:I372GF3W","canonical_record":{"source":{"id":"2402.12177","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T14:33:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d8135ffb2003fa1c8cf68d17990aeed320b973eb3e4c10f2e8a3cf706490ec39","abstract_canon_sha256":"9d6278e5c0fb1c204e365638de18396babbf50a030dc1c9185e54cb7da0ce5ca"},"schema_version":"1.0"},"canonical_sha256":"46ffa3177662d59dd4b396f3750f8db4c02cd77964bdab87b531fd8bb6d663c1","source":{"kind":"arxiv","id":"2402.12177","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I372GF3WMLKZ3VFTS3ZXKD4NWT","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12177","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T14:33:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d8135ffb2003fa1c8cf68d17990aeed320b973eb3e4c10f2e8a3cf706490ec39","abstract_canon_sha256":"9d6278e5c0fb1c204e365638de18396babbf50a030dc1c9185e54cb7da0ce5ca"},"schema_version":"1.0"},"canonical_sha256":"46ffa3177662d59dd4b396f3750f8db4c02cd77964bdab87b531fd8bb6d663c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:14.360740Z","signature_b64":"HKgtl66TNpAv1VyeyCDotMePYdHZgkkzVGAwOt6LpIndMGOGRv4bgL35XT/RmPHC1NtCTx7au8zXDg5vVx58Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46ffa3177662d59dd4b396f3750f8db4c02cd77964bdab87b531fd8bb6d663c1","last_reissued_at":"2026-07-05T07:55:14.360269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:14.360269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12177","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:55:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJbdIRxbuFmNIme3uL5ht/B0xFx0dwUiYIjzjiK2yYUVZW8EPrcyypRz7BksFbeJX2gm+f53SKPg0xzWHZ39Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:25:47.645335Z"},"content_sha256":"c7675a813f37c20e2c8c35f0ef4b9a3a926d30f68afc365dd14b6128c161bd91","schema_version":"1.0","event_id":"sha256:c7675a813f37c20e2c8c35f0ef4b9a3a926d30f68afc365dd14b6128c161bd91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I372GF3WMLKZ3VFTS3ZXKD4NWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"David Barber, Mingtian Zhang, Peter Hayes, Shawn Lan","submitted_at":"2024-02-19T14:33:24Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12177","kind":"arxiv","version":4},"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/2402.12177/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:55:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X9C02fyM+v0bxDv2IhoubGr0FoucycWZ1OWl+ArfuIKNzHfdriTc/h394drlUymBboVA8K6su5YyjGO9Q+dMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:25:47.645704Z"},"content_sha256":"a9880edf206a68d67731ec32b7e14293b8377a7839c2b844512ce54af9180818","schema_version":"1.0","event_id":"sha256:a9880edf206a68d67731ec32b7e14293b8377a7839c2b844512ce54af9180818"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I372GF3WMLKZ3VFTS3ZXKD4NWT/bundle.json","state_url":"https://pith.science/pith/I372GF3WMLKZ3VFTS3ZXKD4NWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I372GF3WMLKZ3VFTS3ZXKD4NWT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T09:25:47Z","links":{"resolver":"https://pith.science/pith/I372GF3WMLKZ3VFTS3ZXKD4NWT","bundle":"https://pith.science/pith/I372GF3WMLKZ3VFTS3ZXKD4NWT/bundle.json","state":"https://pith.science/pith/I372GF3WMLKZ3VFTS3ZXKD4NWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I372GF3WMLKZ3VFTS3ZXKD4NWT/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/Ndy7gEb1M2HPNJ7m6NsCK5Ez5srR2b7ZLU1JZ+HaeRKE5TVLsPNUABO+NB2TTWFtkE+l2/AprjrxnfBaubBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:25:47.647598Z","bundle_sha256":"f9cbacb79fd9c5886d4bb07a82e7a6bbb11d2774a06c5029b8052c1451a1602e"}}