{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XNFEI2PN6ARUQQUNTQVNY6JWIV","short_pith_number":"pith:XNFEI2PN","canonical_record":{"source":{"id":"2207.04237","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-09T09:57:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1241cf0e32e98cbbfa869ea285c05c7abd5dd34279a7b2db7b4f04f4e0b2c393","abstract_canon_sha256":"3d7ab6777dc91efecbc8b6fedc661e345ba82dff39145d63a16f5234405018d8"},"schema_version":"1.0"},"canonical_sha256":"bb4a4469edf02348428d9c2adc7936456d700fe4426c126cb12c588c37b58732","source":{"kind":"arxiv","id":"2207.04237","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04237","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04237v2","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04237","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"pith_short_12","alias_value":"XNFEI2PN6ARU","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"pith_short_16","alias_value":"XNFEI2PN6ARUQQUN","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"pith_short_8","alias_value":"XNFEI2PN","created_at":"2026-07-05T04:55:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XNFEI2PN6ARUQQUNTQVNY6JWIV","target":"record","payload":{"canonical_record":{"source":{"id":"2207.04237","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-09T09:57:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1241cf0e32e98cbbfa869ea285c05c7abd5dd34279a7b2db7b4f04f4e0b2c393","abstract_canon_sha256":"3d7ab6777dc91efecbc8b6fedc661e345ba82dff39145d63a16f5234405018d8"},"schema_version":"1.0"},"canonical_sha256":"bb4a4469edf02348428d9c2adc7936456d700fe4426c126cb12c588c37b58732","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:39.576579Z","signature_b64":"y0r8ExeDEyBQyPx+hW67+3AvABhmTG0ATyBfQXkqNp8W3RbP+jaFktjSwv+AngSwRdvr3pBH3YEAhljedeNODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb4a4469edf02348428d9c2adc7936456d700fe4426c126cb12c588c37b58732","last_reissued_at":"2026-07-05T04:55:39.576156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:39.576156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.04237","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":"2026-07-05T04:55:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJSGXXrrA2NKIM9XPHTan63M52ReL/U+rbxPrtR398LgpMArhMZkndorZQwR5tKtR8dC/29tt+YTUbh7lKCuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:37:48.967214Z"},"content_sha256":"6645ee9ce2927e0520276213fa8dc198cbed6b51aedd7cd215ed964bdcf649e4","schema_version":"1.0","event_id":"sha256:6645ee9ce2927e0520276213fa8dc198cbed6b51aedd7cd215ed964bdcf649e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XNFEI2PN6ARUQQUNTQVNY6JWIV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-shot training LLMs for project-specific code-summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Premkumar Devanbu, Toufique Ahmed","submitted_at":"2022-07-09T09:57:11Z","abstract_excerpt":"Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A particularly exciting aspect of LLMs is their knack for few-shot and zero-shot learning: they can learn to perform a task with very few examples. Few-shotting has particular synergies in software engineering, where there are a lot of phenomena (identifier names, APIs, terminology, coding patterns) that are known to be highly project-specific. However, project-specific data can be quite limited, especially early in the h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04237","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/2207.04237/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":"2026-07-05T04:55:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BwgymzfkhyoMbVkW7rAU/AbMFtDPcG7+JB1Z76WZzh6225tBG0H+mThJoD0R0Y/yCF52HfM3davbYbbd2GA0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:37:48.968150Z"},"content_sha256":"15227e5fba24f112d96ba3bbb7a9dda00a56029e16ad9ff98c66d53ca0f4ed5d","schema_version":"1.0","event_id":"sha256:15227e5fba24f112d96ba3bbb7a9dda00a56029e16ad9ff98c66d53ca0f4ed5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XNFEI2PN6ARUQQUNTQVNY6JWIV/bundle.json","state_url":"https://pith.science/pith/XNFEI2PN6ARUQQUNTQVNY6JWIV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XNFEI2PN6ARUQQUNTQVNY6JWIV/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":"2026-08-19T19:37:48Z","links":{"resolver":"https://pith.science/pith/XNFEI2PN6ARUQQUNTQVNY6JWIV","bundle":"https://pith.science/pith/XNFEI2PN6ARUQQUNTQVNY6JWIV/bundle.json","state":"https://pith.science/pith/XNFEI2PN6ARUQQUNTQVNY6JWIV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XNFEI2PN6ARUQQUNTQVNY6JWIV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XNFEI2PN6ARUQQUNTQVNY6JWIV","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":"3d7ab6777dc91efecbc8b6fedc661e345ba82dff39145d63a16f5234405018d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-09T09:57:11Z","title_canon_sha256":"1241cf0e32e98cbbfa869ea285c05c7abd5dd34279a7b2db7b4f04f4e0b2c393"},"schema_version":"1.0","source":{"id":"2207.04237","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04237","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04237v2","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04237","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"pith_short_12","alias_value":"XNFEI2PN6ARU","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"pith_short_16","alias_value":"XNFEI2PN6ARUQQUN","created_at":"2026-07-05T04:55:39Z"},{"alias_kind":"pith_short_8","alias_value":"XNFEI2PN","created_at":"2026-07-05T04:55:39Z"}],"graph_snapshots":[{"event_id":"sha256:15227e5fba24f112d96ba3bbb7a9dda00a56029e16ad9ff98c66d53ca0f4ed5d","target":"graph","created_at":"2026-07-05T04:55:39Z","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/2207.04237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A particularly exciting aspect of LLMs is their knack for few-shot and zero-shot learning: they can learn to perform a task with very few examples. Few-shotting has particular synergies in software engineering, where there are a lot of phenomena (identifier names, APIs, terminology, coding patterns) that are known to be highly project-specific. However, project-specific data can be quite limited, especially early in the h","authors_text":"Premkumar Devanbu, Toufique Ahmed","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-09T09:57:11Z","title":"Few-shot training LLMs for project-specific code-summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04237","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":"sha256:6645ee9ce2927e0520276213fa8dc198cbed6b51aedd7cd215ed964bdcf649e4","target":"record","created_at":"2026-07-05T04:55:39Z","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":"3d7ab6777dc91efecbc8b6fedc661e345ba82dff39145d63a16f5234405018d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-09T09:57:11Z","title_canon_sha256":"1241cf0e32e98cbbfa869ea285c05c7abd5dd34279a7b2db7b4f04f4e0b2c393"},"schema_version":"1.0","source":{"id":"2207.04237","kind":"arxiv","version":2}},"canonical_sha256":"bb4a4469edf02348428d9c2adc7936456d700fe4426c126cb12c588c37b58732","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb4a4469edf02348428d9c2adc7936456d700fe4426c126cb12c588c37b58732","first_computed_at":"2026-07-05T04:55:39.576156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:55:39.576156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y0r8ExeDEyBQyPx+hW67+3AvABhmTG0ATyBfQXkqNp8W3RbP+jaFktjSwv+AngSwRdvr3pBH3YEAhljedeNODw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:55:39.576579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.04237","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6645ee9ce2927e0520276213fa8dc198cbed6b51aedd7cd215ed964bdcf649e4","sha256:15227e5fba24f112d96ba3bbb7a9dda00a56029e16ad9ff98c66d53ca0f4ed5d"],"state_sha256":"6f11fe68540e60fe3e791d60edcdf4013b734a3ebb67a552fa0a7594b9aaf89f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FopYfIxBRehKMfESzsn83n+nT9JJJ8jdA9LT6SUznNb9b4gNtrl6CPULBvz/RuCLcB721NySbdQgbZOQXE1LDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:37:48.974944Z","bundle_sha256":"dedde32e367a4f4b4a3cb3c18ae33802d7a958d50792b560b89bf3c1f7a84b01"}}