{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DYCC66IHCK3TNFARX7OEV22CIK","short_pith_number":"pith:DYCC66IH","canonical_record":{"source":{"id":"2402.16829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:55:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5a8de37e6044fdd1e5391c3eaacfcec83f4808f6c73f2b24c8e3c2be80e86e05","abstract_canon_sha256":"55ef3d50b9c79d92d43567fde3fd816878d3e56a5f77d591037f770ce01751a1"},"schema_version":"1.0"},"canonical_sha256":"1e042f790712b7369411bfdc4aeb4242aab4d29d526965d909af2189a8c01fb3","source":{"kind":"arxiv","id":"2402.16829","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16829","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16829v1","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16829","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_12","alias_value":"DYCC66IHCK3T","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_16","alias_value":"DYCC66IHCK3TNFAR","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_8","alias_value":"DYCC66IH","created_at":"2026-07-05T07:49:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DYCC66IHCK3TNFARX7OEV22CIK","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:55:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5a8de37e6044fdd1e5391c3eaacfcec83f4808f6c73f2b24c8e3c2be80e86e05","abstract_canon_sha256":"55ef3d50b9c79d92d43567fde3fd816878d3e56a5f77d591037f770ce01751a1"},"schema_version":"1.0"},"canonical_sha256":"1e042f790712b7369411bfdc4aeb4242aab4d29d526965d909af2189a8c01fb3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:26.517847Z","signature_b64":"jREUbTkhmwDQ+ZNd+oPI8XKIg9ntfjTWS9rVO8QXRANJqPxm2F/J2fK60vF/ANIAIHBaahg7fttQ0SeogAWkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e042f790712b7369411bfdc4aeb4242aab4d29d526965d909af2189a8c01fb3","last_reissued_at":"2026-07-05T07:49:26.517363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:26.517363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16829","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:49:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAhep1qQBOZZe8jlYds4M7XccKJuR0sSAFzdKqle1ld6TM3cmLhTgqvSaE6tl6hDoVijmrS4CsP63P0H504hBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:16:39.099850Z"},"content_sha256":"7d15964c33e5fa33786a7f5f4dfe9994d654fe4fbfd7cc47356b9dc4dbfef347","schema_version":"1.0","event_id":"sha256:7d15964c33e5fa33786a7f5f4dfe9994d654fe4fbfd7cc47356b9dc4dbfef347"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DYCC66IHCK3TNFARX7OEV22CIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aivin V. Solatorio","submitted_at":"2024-02-26T18:55:15Z","abstract_excerpt":"Embedding models are integral to AI applications like semantic search, personalized recommendations, and retrieval augmented generation for LLMs, necessitating high-quality training data. However, the limited scalability of manual data curation prompts the need for automated methods to ensure data integrity. Traditional unsupervised triplet mining automates training data generation, crucial for embedding model training, yet inadvertently injects biases and noise, thereby degrading model performance. Addressing this, we introduce GISTEmbed, a novel strategy that enhances in-batch negative selec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16829","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/2402.16829/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":"2026-07-05T07:49:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9h905RDWiqasJCMIYVpw2LcdqEC0cT86Pty5e89nmLKwyY+lwt8Bi7sOhKEPBTuMkDHVnbn816N0veV7RWADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:16:39.100353Z"},"content_sha256":"ea8a98f1ed823c8c6e612b45bfcb857a37442e2f3d17af633797e698ffca9e5f","schema_version":"1.0","event_id":"sha256:ea8a98f1ed823c8c6e612b45bfcb857a37442e2f3d17af633797e698ffca9e5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYCC66IHCK3TNFARX7OEV22CIK/bundle.json","state_url":"https://pith.science/pith/DYCC66IHCK3TNFARX7OEV22CIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYCC66IHCK3TNFARX7OEV22CIK/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":"2026-08-07T12:16:39Z","links":{"resolver":"https://pith.science/pith/DYCC66IHCK3TNFARX7OEV22CIK","bundle":"https://pith.science/pith/DYCC66IHCK3TNFARX7OEV22CIK/bundle.json","state":"https://pith.science/pith/DYCC66IHCK3TNFARX7OEV22CIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYCC66IHCK3TNFARX7OEV22CIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DYCC66IHCK3TNFARX7OEV22CIK","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":"55ef3d50b9c79d92d43567fde3fd816878d3e56a5f77d591037f770ce01751a1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:55:15Z","title_canon_sha256":"5a8de37e6044fdd1e5391c3eaacfcec83f4808f6c73f2b24c8e3c2be80e86e05"},"schema_version":"1.0","source":{"id":"2402.16829","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16829","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16829v1","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16829","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_12","alias_value":"DYCC66IHCK3T","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_16","alias_value":"DYCC66IHCK3TNFAR","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_8","alias_value":"DYCC66IH","created_at":"2026-07-05T07:49:26Z"}],"graph_snapshots":[{"event_id":"sha256:ea8a98f1ed823c8c6e612b45bfcb857a37442e2f3d17af633797e698ffca9e5f","target":"graph","created_at":"2026-07-05T07:49:26Z","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/2402.16829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embedding models are integral to AI applications like semantic search, personalized recommendations, and retrieval augmented generation for LLMs, necessitating high-quality training data. However, the limited scalability of manual data curation prompts the need for automated methods to ensure data integrity. Traditional unsupervised triplet mining automates training data generation, crucial for embedding model training, yet inadvertently injects biases and noise, thereby degrading model performance. Addressing this, we introduce GISTEmbed, a novel strategy that enhances in-batch negative selec","authors_text":"Aivin V. Solatorio","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:55:15Z","title":"GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16829","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":"sha256:7d15964c33e5fa33786a7f5f4dfe9994d654fe4fbfd7cc47356b9dc4dbfef347","target":"record","created_at":"2026-07-05T07:49:26Z","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":"55ef3d50b9c79d92d43567fde3fd816878d3e56a5f77d591037f770ce01751a1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:55:15Z","title_canon_sha256":"5a8de37e6044fdd1e5391c3eaacfcec83f4808f6c73f2b24c8e3c2be80e86e05"},"schema_version":"1.0","source":{"id":"2402.16829","kind":"arxiv","version":1}},"canonical_sha256":"1e042f790712b7369411bfdc4aeb4242aab4d29d526965d909af2189a8c01fb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e042f790712b7369411bfdc4aeb4242aab4d29d526965d909af2189a8c01fb3","first_computed_at":"2026-07-05T07:49:26.517363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:26.517363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jREUbTkhmwDQ+ZNd+oPI8XKIg9ntfjTWS9rVO8QXRANJqPxm2F/J2fK60vF/ANIAIHBaahg7fttQ0SeogAWkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:26.517847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16829","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d15964c33e5fa33786a7f5f4dfe9994d654fe4fbfd7cc47356b9dc4dbfef347","sha256:ea8a98f1ed823c8c6e612b45bfcb857a37442e2f3d17af633797e698ffca9e5f"],"state_sha256":"149cf12e348f86dcdb9167b91cc2caeb2f11f4dfa353665426e60130c9be9402"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eztRdm1Zte1+fjSPsB5+Xf59DYiF8tckJUq1C7ra9Jm20IAJlUJbSnc764L7Wxi02K1K5cKFMMzKbK+g1wuAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:16:39.120435Z","bundle_sha256":"a823a00222b3e42cb51d77d36d484f13fa495066c6aa2121c584697730989e48"}}