{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BMBQOAO7BVAOAGCK6KHQDLT6RA","short_pith_number":"pith:BMBQOAO7","canonical_record":{"source":{"id":"2306.03268","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T21:38:30Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"785f4560aec91b3a14cb8294ffa2ef202a77b5b293270eea7b75691108322666","abstract_canon_sha256":"c32f9c5a80dc44fc5009debf9ffec0a9c5ac8eeb2c47e107b2059ae4973749aa"},"schema_version":"1.0"},"canonical_sha256":"0b030701df0d40e0184af28f01ae7e8835f5ea5031b7031c85e18f4337bdea39","source":{"kind":"arxiv","id":"2306.03268","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03268","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03268v3","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03268","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"BMBQOAO7BVAO","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"BMBQOAO7BVAOAGCK","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"BMBQOAO7","created_at":"2026-07-05T10:17:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BMBQOAO7BVAOAGCK6KHQDLT6RA","target":"record","payload":{"canonical_record":{"source":{"id":"2306.03268","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T21:38:30Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"785f4560aec91b3a14cb8294ffa2ef202a77b5b293270eea7b75691108322666","abstract_canon_sha256":"c32f9c5a80dc44fc5009debf9ffec0a9c5ac8eeb2c47e107b2059ae4973749aa"},"schema_version":"1.0"},"canonical_sha256":"0b030701df0d40e0184af28f01ae7e8835f5ea5031b7031c85e18f4337bdea39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:45.021617Z","signature_b64":"CjuFh4qOgeEYY6dvl4FDCbUxxoUCIjiH334iB82qRDin+FFnJVvddB0bwuZffLXxphg9oX+f1gRZX7KwEFiVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b030701df0d40e0184af28f01ae7e8835f5ea5031b7031c85e18f4337bdea39","last_reissued_at":"2026-07-05T10:17:45.021128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:45.021128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.03268","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aqJYKlQ9HJD8CpQt5C/o6xdzmOJfwg4PT6k8py4T+agnHfmD+hV0buNFUyDybXHnEvkYg6hN2C552/HSSyqBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:57:20.542857Z"},"content_sha256":"5d9beda9aa0f847a0242d467e0a64ca1c6bfbf01846f59cecff2e8c940bd37c8","schema_version":"1.0","event_id":"sha256:5d9beda9aa0f847a0242d467e0a64ca1c6bfbf01846f59cecff2e8c940bd37c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BMBQOAO7BVAOAGCK6KHQDLT6RA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skill over Scale: The Case for Medium, Domain-Specific Models for SE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Manisha Mukherjee, Vincent J. Hellendoorn","submitted_at":"2023-06-05T21:38:30Z","abstract_excerpt":"Recent advancements in AI have sparked a trend in constructing large, generalist language models that handle a multitude of tasks, including many code-related ones. While these models are expensive to train and are often closed-source, they have enjoyed broad adoption because they tend to outperform smaller, domain-specific models of code. In this work, we argue that this is not a foregone conclusion. We show that modestly sized domain-specific models can outperform much larger ones on code labeling tasks, provided they are trained to the same standards. Concretely, we focus on StackOverflow ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03268","kind":"arxiv","version":3},"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/2306.03268/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":"2026-07-05T10:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNoHY1F91j1BKiEYPy9ApRm3LIUnfC0SH1ujOubvsi5qZ99jc7PStAE/pO6BpTN1AWugYaGQ0KqR5xUgQMsOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:57:20.543616Z"},"content_sha256":"fb437bc931cfb3e70c9a65f42da5df11d4e97f1247376fd6b0f55c2f15f63888","schema_version":"1.0","event_id":"sha256:fb437bc931cfb3e70c9a65f42da5df11d4e97f1247376fd6b0f55c2f15f63888"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMBQOAO7BVAOAGCK6KHQDLT6RA/bundle.json","state_url":"https://pith.science/pith/BMBQOAO7BVAOAGCK6KHQDLT6RA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMBQOAO7BVAOAGCK6KHQDLT6RA/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":"2026-08-11T01:57:20Z","links":{"resolver":"https://pith.science/pith/BMBQOAO7BVAOAGCK6KHQDLT6RA","bundle":"https://pith.science/pith/BMBQOAO7BVAOAGCK6KHQDLT6RA/bundle.json","state":"https://pith.science/pith/BMBQOAO7BVAOAGCK6KHQDLT6RA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMBQOAO7BVAOAGCK6KHQDLT6RA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BMBQOAO7BVAOAGCK6KHQDLT6RA","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":"c32f9c5a80dc44fc5009debf9ffec0a9c5ac8eeb2c47e107b2059ae4973749aa","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T21:38:30Z","title_canon_sha256":"785f4560aec91b3a14cb8294ffa2ef202a77b5b293270eea7b75691108322666"},"schema_version":"1.0","source":{"id":"2306.03268","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03268","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03268v3","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03268","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"BMBQOAO7BVAO","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"BMBQOAO7BVAOAGCK","created_at":"2026-07-05T10:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"BMBQOAO7","created_at":"2026-07-05T10:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:fb437bc931cfb3e70c9a65f42da5df11d4e97f1247376fd6b0f55c2f15f63888","target":"graph","created_at":"2026-07-05T10:17:45Z","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/2306.03268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in AI have sparked a trend in constructing large, generalist language models that handle a multitude of tasks, including many code-related ones. While these models are expensive to train and are often closed-source, they have enjoyed broad adoption because they tend to outperform smaller, domain-specific models of code. In this work, we argue that this is not a foregone conclusion. We show that modestly sized domain-specific models can outperform much larger ones on code labeling tasks, provided they are trained to the same standards. Concretely, we focus on StackOverflow (","authors_text":"Manisha Mukherjee, Vincent J. Hellendoorn","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T21:38:30Z","title":"Skill over Scale: The Case for Medium, Domain-Specific Models for SE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03268","kind":"arxiv","version":3},"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":"sha256:5d9beda9aa0f847a0242d467e0a64ca1c6bfbf01846f59cecff2e8c940bd37c8","target":"record","created_at":"2026-07-05T10:17:45Z","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":"c32f9c5a80dc44fc5009debf9ffec0a9c5ac8eeb2c47e107b2059ae4973749aa","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T21:38:30Z","title_canon_sha256":"785f4560aec91b3a14cb8294ffa2ef202a77b5b293270eea7b75691108322666"},"schema_version":"1.0","source":{"id":"2306.03268","kind":"arxiv","version":3}},"canonical_sha256":"0b030701df0d40e0184af28f01ae7e8835f5ea5031b7031c85e18f4337bdea39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b030701df0d40e0184af28f01ae7e8835f5ea5031b7031c85e18f4337bdea39","first_computed_at":"2026-07-05T10:17:45.021128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:45.021128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CjuFh4qOgeEYY6dvl4FDCbUxxoUCIjiH334iB82qRDin+FFnJVvddB0bwuZffLXxphg9oX+f1gRZX7KwEFiVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:45.021617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03268","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d9beda9aa0f847a0242d467e0a64ca1c6bfbf01846f59cecff2e8c940bd37c8","sha256:fb437bc931cfb3e70c9a65f42da5df11d4e97f1247376fd6b0f55c2f15f63888"],"state_sha256":"09dd6cdff70c1ba3f14c0e1775c9332148827991841121f30d1b3f9a5a8380e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v53I8V7KuOFNaLARbGqEl73l/CiJFvGnuN/thTaCshSJDMDImI4qRSclNS/xfY5UPNZSqZxwHesqz3HCRkddDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:57:20.549796Z","bundle_sha256":"75cd439c0e4b371dfce1d648bf6a6c1bff7c30749619e58e3975552bfc9b19ea"}}