{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GHVQR7JSRFWBHXL35E5OQQNN4F","short_pith_number":"pith:GHVQR7JS","canonical_record":{"source":{"id":"1904.02660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T16:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"c09552e0e27e4a41c966252d29e372fa15f7503aa99117370725887f28c3bcdf","abstract_canon_sha256":"30e00dcbcfd8b000e7b2bf342574f97528d5152c804d7a87e24a141cd520df47"},"schema_version":"1.0"},"canonical_sha256":"31eb08fd32896c13dd7be93ae841ade143a81e31747d7e851a216a6fb09f4a57","source":{"kind":"arxiv","id":"1904.02660","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.02660","created_at":"2026-05-17T23:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"1904.02660v1","created_at":"2026-05-17T23:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02660","created_at":"2026-05-17T23:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"GHVQR7JSRFWB","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GHVQR7JSRFWBHXL3","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GHVQR7JS","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GHVQR7JSRFWBHXL35E5OQQNN4F","target":"record","payload":{"canonical_record":{"source":{"id":"1904.02660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T16:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"c09552e0e27e4a41c966252d29e372fa15f7503aa99117370725887f28c3bcdf","abstract_canon_sha256":"30e00dcbcfd8b000e7b2bf342574f97528d5152c804d7a87e24a141cd520df47"},"schema_version":"1.0"},"canonical_sha256":"31eb08fd32896c13dd7be93ae841ade143a81e31747d7e851a216a6fb09f4a57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:23.085525Z","signature_b64":"ZA1/XiCDoKG2OsTBmH5cDJBuUtW6Aqw2/x9iWfKct9d1uJ01eTMyHugNTYhN0FVgRJkvew5il+TVJRhIiFrMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31eb08fd32896c13dd7be93ae841ade143a81e31747d7e851a216a6fb09f4a57","last_reissued_at":"2026-05-17T23:49:23.084973Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:23.084973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.02660","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":"2026-05-17T23:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Do/we3i43ck46WR3AA1FqAK72CrtPSIF/hkJwLDPX7AhDqHKQQ4dlgPuCJ5ulZfr35XGXlyUuAANJJ9dxeTbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T00:35:01.163376Z"},"content_sha256":"8ffe347a0b5f5e836dd1336978db03b1c0b7ea14644c581f838064c57fa796f2","schema_version":"1.0","event_id":"sha256:8ffe347a0b5f5e836dd1336978db03b1c0b7ea14644c581f838064c57fa796f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GHVQR7JSRFWBHXL35E5OQQNN4F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recommendations for Datasets for Source Code Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander LeClair, Collin McMillan","submitted_at":"2019-04-04T16:56:01Z","abstract_excerpt":"Source Code Summarization is the task of writing short, natural language descriptions of source code. The main use for these descriptions is in software documentation e.g. the one-sentence Java method descriptions in JavaDocs. Code summarization is rapidly becoming a popular research problem, but progress is restrained due to a lack of suitable datasets. In addition, a lack of community standards for creating datasets leads to confusing and unreproducible research results -- we observe swings in performance of more than 33% due only to changes in dataset design. In this paper, we make recommen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02660","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":""},"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":"2026-05-17T23:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qp2L7c6HtEXJ/VD/gzWGTytaSGDvt6ER64t3EefHgAyaj+S+6sr/vq+S8Ya6ULwlIxQYaWP5GwY2Q892P3NOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T00:35:01.163718Z"},"content_sha256":"f25f5166a93f6ed0213ddc72ec74142277d7890088fa62c0906ee0526a8a8474","schema_version":"1.0","event_id":"sha256:f25f5166a93f6ed0213ddc72ec74142277d7890088fa62c0906ee0526a8a8474"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/bundle.json","state_url":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/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":"2026-07-05T00:35:01Z","links":{"resolver":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F","bundle":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/bundle.json","state":"https://pith.science/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHVQR7JSRFWBHXL35E5OQQNN4F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GHVQR7JSRFWBHXL35E5OQQNN4F","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":"30e00dcbcfd8b000e7b2bf342574f97528d5152c804d7a87e24a141cd520df47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T16:56:01Z","title_canon_sha256":"c09552e0e27e4a41c966252d29e372fa15f7503aa99117370725887f28c3bcdf"},"schema_version":"1.0","source":{"id":"1904.02660","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.02660","created_at":"2026-05-17T23:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"1904.02660v1","created_at":"2026-05-17T23:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02660","created_at":"2026-05-17T23:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"GHVQR7JSRFWB","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GHVQR7JSRFWBHXL3","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GHVQR7JS","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:f25f5166a93f6ed0213ddc72ec74142277d7890088fa62c0906ee0526a8a8474","target":"graph","created_at":"2026-05-17T23:49:23Z","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"},"paper":{"abstract_excerpt":"Source Code Summarization is the task of writing short, natural language descriptions of source code. The main use for these descriptions is in software documentation e.g. the one-sentence Java method descriptions in JavaDocs. Code summarization is rapidly becoming a popular research problem, but progress is restrained due to a lack of suitable datasets. In addition, a lack of community standards for creating datasets leads to confusing and unreproducible research results -- we observe swings in performance of more than 33% due only to changes in dataset design. In this paper, we make recommen","authors_text":"Alexander LeClair, Collin McMillan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T16:56:01Z","title":"Recommendations for Datasets for Source Code Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02660","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":"sha256:8ffe347a0b5f5e836dd1336978db03b1c0b7ea14644c581f838064c57fa796f2","target":"record","created_at":"2026-05-17T23:49:23Z","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":"30e00dcbcfd8b000e7b2bf342574f97528d5152c804d7a87e24a141cd520df47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T16:56:01Z","title_canon_sha256":"c09552e0e27e4a41c966252d29e372fa15f7503aa99117370725887f28c3bcdf"},"schema_version":"1.0","source":{"id":"1904.02660","kind":"arxiv","version":1}},"canonical_sha256":"31eb08fd32896c13dd7be93ae841ade143a81e31747d7e851a216a6fb09f4a57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31eb08fd32896c13dd7be93ae841ade143a81e31747d7e851a216a6fb09f4a57","first_computed_at":"2026-05-17T23:49:23.084973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:23.084973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZA1/XiCDoKG2OsTBmH5cDJBuUtW6Aqw2/x9iWfKct9d1uJ01eTMyHugNTYhN0FVgRJkvew5il+TVJRhIiFrMDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:23.085525Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.02660","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ffe347a0b5f5e836dd1336978db03b1c0b7ea14644c581f838064c57fa796f2","sha256:f25f5166a93f6ed0213ddc72ec74142277d7890088fa62c0906ee0526a8a8474"],"state_sha256":"73fd40e3ac96722fd8b587ef2f0cfbf356b1ce7f3002486caf7c52d9570eb761"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mfvtcnlK8asXINTeomEIRiwRqgP0gw6pvnx4qqV8gvLuQ/vvmbr4eiVWUU7SeNZnvs96F0gC+aoC/WwSrpcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T00:35:01.165552Z","bundle_sha256":"41bfda8db2e3fd24d904b0632fe559f91266d8ea350c9d2c04c374805d10331d"}}