{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FL4BC3XRYZGJY4N252GQHI5Q65","short_pith_number":"pith:FL4BC3XR","canonical_record":{"source":{"id":"2310.17228","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T08:27:36Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"4d858c19c53165db56c6a41d398b69c7bcf1d5fd348231ad0a30f099d3ecf4a1","abstract_canon_sha256":"cbd8feb8f22d76780a68c30954b7aee9dbcef9a2e6443f7897e9b6379ab4cf49"},"schema_version":"1.0"},"canonical_sha256":"2af8116ef1c64c9c71baee8d03a3b0f76e96cae1afd7b4cdf0040fe3b793f469","source":{"kind":"arxiv","id":"2310.17228","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17228","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17228v2","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17228","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"FL4BC3XRYZGJ","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"FL4BC3XRYZGJY4N2","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"FL4BC3XR","created_at":"2026-07-05T07:06:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FL4BC3XRYZGJY4N252GQHI5Q65","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17228","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T08:27:36Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"4d858c19c53165db56c6a41d398b69c7bcf1d5fd348231ad0a30f099d3ecf4a1","abstract_canon_sha256":"cbd8feb8f22d76780a68c30954b7aee9dbcef9a2e6443f7897e9b6379ab4cf49"},"schema_version":"1.0"},"canonical_sha256":"2af8116ef1c64c9c71baee8d03a3b0f76e96cae1afd7b4cdf0040fe3b793f469","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:06.465140Z","signature_b64":"gvURi2xhylKPwYIBzozxVHM8dDhkzy9oDuw8cvTXjFRze222xJK67DKshlG8e9qgZ2A+qwVj/GI0nRQs0IscCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2af8116ef1c64c9c71baee8d03a3b0f76e96cae1afd7b4cdf0040fe3b793f469","last_reissued_at":"2026-07-05T07:06:06.464657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:06.464657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17228","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:06:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R6ZO+yQFJGky9MSi3TpBiXC1F8IjtYVb2WHsv2WbM+z6GP3OtvDQtYFTQv/qCnOw9Gvz55/slRFozlFxsX7oDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:18:06.980095Z"},"content_sha256":"ea1a6c4dcfa6b080b936a57d3b98b7f232a4f6e44486a376d5805769fcb417ee","schema_version":"1.0","event_id":"sha256:ea1a6c4dcfa6b080b936a57d3b98b7f232a4f6e44486a376d5805769fcb417ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FL4BC3XRYZGJY4N252GQHI5Q65","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TST$^\\mathrm{R}$: Target Similarity Tuning Meets the Real World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.AI","authors_text":"Ananya Singha, Anirudh Khatry, Gust Verbruggen, Mukul Singh, Priyanshu Gupta, Sumit Gulwani, Vu Le","submitted_at":"2023-10-26T08:27:36Z","abstract_excerpt":"Target similarity tuning (TST) is a method of selecting relevant examples in natural language (NL) to code generation through large language models (LLMs) to improve performance. Its goal is to adapt a sentence embedding model to have the similarity between two NL inputs match the similarity between their associated code outputs. In this paper, we propose different methods to apply and improve TST in the real world. First, we replace the sentence transformer with embeddings from a larger model, which reduces sensitivity to the language distribution and thus provides more flexibility in synthet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17228","kind":"arxiv","version":2},"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/2310.17228/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":"2026-07-05T07:06:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vXPBGjmEFcODDunba1ot2gjaaVey/wB9c/e3+aGBhaO2Rz6AZPEqybjfm/IAuAkyizP6ZSTmOziI4cdj8Lx+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:18:06.980628Z"},"content_sha256":"d70bc1456a7a043432d21e4155d447473e4c3d77c85a933dd93145630574f7e8","schema_version":"1.0","event_id":"sha256:d70bc1456a7a043432d21e4155d447473e4c3d77c85a933dd93145630574f7e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FL4BC3XRYZGJY4N252GQHI5Q65/bundle.json","state_url":"https://pith.science/pith/FL4BC3XRYZGJY4N252GQHI5Q65/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FL4BC3XRYZGJY4N252GQHI5Q65/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":"2026-08-16T18:18:06Z","links":{"resolver":"https://pith.science/pith/FL4BC3XRYZGJY4N252GQHI5Q65","bundle":"https://pith.science/pith/FL4BC3XRYZGJY4N252GQHI5Q65/bundle.json","state":"https://pith.science/pith/FL4BC3XRYZGJY4N252GQHI5Q65/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FL4BC3XRYZGJY4N252GQHI5Q65/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FL4BC3XRYZGJY4N252GQHI5Q65","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":"cbd8feb8f22d76780a68c30954b7aee9dbcef9a2e6443f7897e9b6379ab4cf49","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T08:27:36Z","title_canon_sha256":"4d858c19c53165db56c6a41d398b69c7bcf1d5fd348231ad0a30f099d3ecf4a1"},"schema_version":"1.0","source":{"id":"2310.17228","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17228","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17228v2","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17228","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"FL4BC3XRYZGJ","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"FL4BC3XRYZGJY4N2","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"FL4BC3XR","created_at":"2026-07-05T07:06:06Z"}],"graph_snapshots":[{"event_id":"sha256:d70bc1456a7a043432d21e4155d447473e4c3d77c85a933dd93145630574f7e8","target":"graph","created_at":"2026-07-05T07:06:06Z","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/2310.17228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target similarity tuning (TST) is a method of selecting relevant examples in natural language (NL) to code generation through large language models (LLMs) to improve performance. Its goal is to adapt a sentence embedding model to have the similarity between two NL inputs match the similarity between their associated code outputs. In this paper, we propose different methods to apply and improve TST in the real world. First, we replace the sentence transformer with embeddings from a larger model, which reduces sensitivity to the language distribution and thus provides more flexibility in synthet","authors_text":"Ananya Singha, Anirudh Khatry, Gust Verbruggen, Mukul Singh, Priyanshu Gupta, Sumit Gulwani, Vu Le","cross_cats":["cs.CL","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T08:27:36Z","title":"TST$^\\mathrm{R}$: Target Similarity Tuning Meets the Real World"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17228","kind":"arxiv","version":2},"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:ea1a6c4dcfa6b080b936a57d3b98b7f232a4f6e44486a376d5805769fcb417ee","target":"record","created_at":"2026-07-05T07:06:06Z","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":"cbd8feb8f22d76780a68c30954b7aee9dbcef9a2e6443f7897e9b6379ab4cf49","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-26T08:27:36Z","title_canon_sha256":"4d858c19c53165db56c6a41d398b69c7bcf1d5fd348231ad0a30f099d3ecf4a1"},"schema_version":"1.0","source":{"id":"2310.17228","kind":"arxiv","version":2}},"canonical_sha256":"2af8116ef1c64c9c71baee8d03a3b0f76e96cae1afd7b4cdf0040fe3b793f469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2af8116ef1c64c9c71baee8d03a3b0f76e96cae1afd7b4cdf0040fe3b793f469","first_computed_at":"2026-07-05T07:06:06.464657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:06.464657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gvURi2xhylKPwYIBzozxVHM8dDhkzy9oDuw8cvTXjFRze222xJK67DKshlG8e9qgZ2A+qwVj/GI0nRQs0IscCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:06.465140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17228","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea1a6c4dcfa6b080b936a57d3b98b7f232a4f6e44486a376d5805769fcb417ee","sha256:d70bc1456a7a043432d21e4155d447473e4c3d77c85a933dd93145630574f7e8"],"state_sha256":"03fd99bd8a3ea2d9636d9c59a650fc7e807debd48089305d131b6d62e534af06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XlHUBMTVLCfddCObJBlXLv1y/lKdcqrHUZHDkICFi6/wtSFzYSjTnEMGA2+Bp5JpA8awZWj8ulJGlmiolctcBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T18:18:06.984344Z","bundle_sha256":"34711eae0db054e69b940c79844bb4dfac0463a286bac5a15001ce14bb063fd2"}}