{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FXYI4S4AVLAOJI6TT7TL35ZMC6","short_pith_number":"pith:FXYI4S4A","canonical_record":{"source":{"id":"2604.00787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-01T11:53:12Z","cross_cats_sorted":[],"title_canon_sha256":"a703653387299ec58abc4672403b12dc312f77ef3c705eacef890d66a32593c7","abstract_canon_sha256":"2e93966efe2c99411f8bd66d1ed46f5c0efcf1d6227c7b630e310cd33d712bcd"},"schema_version":"1.0"},"canonical_sha256":"2df08e4b80aac0e4a3d39fe6bdf72c1790dae8103545197d972e841d7b905feb","source":{"kind":"arxiv","id":"2604.00787","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.00787","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2604.00787v2","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00787","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"FXYI4S4AVLAO","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"FXYI4S4AVLAOJI6T","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"FXYI4S4A","created_at":"2026-08-04T02:09:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FXYI4S4AVLAOJI6TT7TL35ZMC6","target":"record","payload":{"canonical_record":{"source":{"id":"2604.00787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-01T11:53:12Z","cross_cats_sorted":[],"title_canon_sha256":"a703653387299ec58abc4672403b12dc312f77ef3c705eacef890d66a32593c7","abstract_canon_sha256":"2e93966efe2c99411f8bd66d1ed46f5c0efcf1d6227c7b630e310cd33d712bcd"},"schema_version":"1.0"},"canonical_sha256":"2df08e4b80aac0e4a3d39fe6bdf72c1790dae8103545197d972e841d7b905feb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:09:37.004749Z","signature_b64":"zlUFXqP+EWXUaIHaRwQZwrRVzJrX8x/b0T3Z1EJfgzkxw2dLBtMt8AOtvnlsB9sPs1qD+YwTp7JpS6a4kcbWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2df08e4b80aac0e4a3d39fe6bdf72c1790dae8103545197d972e841d7b905feb","last_reissued_at":"2026-08-04T02:09:37.002797Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:09:37.002797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.00787","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":"2026-08-04T02:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SmKj24IfEa+Es4oVtFtGnTY0ka8i5qe10rojhe6gXcnc75jaFGGRFbmqIKnR6+iso70Qwifx/9E210nfx+NfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:51:58.054779Z"},"content_sha256":"bf7fdeeb8ff08a19e6627abf13650b978f58286ed46b6e0e6a801c9706917ba1","schema_version":"1.0","event_id":"sha256:bf7fdeeb8ff08a19e6627abf13650b978f58286ed46b6e0e6a801c9706917ba1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FXYI4S4AVLAOJI6TT7TL35ZMC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Rise of Language Models in Mining Software Repositories: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ana B. S\\'anchez, Miguel Romero-Arjona, Saman Barakat, Sergio Segura","submitted_at":"2026-04-01T11:53:12Z","abstract_excerpt":"The Mining Software Repositories (MSR) field focuses on analyzing the rich data contained in software repositories to derive actionable insights into software processes and products. Mining repositories at scale requires techniques capable of handling large volumes of heterogeneous data, a challenge for which language models (LMs) are increasingly well-suited. Since the advent of Transformer-based architectures, LMs have been rapidly adopted across a wide range of MSR tasks. This article presents a comprehensive survey of the use of LMs in MSR, based on an analysis of 177 papers. We examine ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00787","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/2604.00787/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":"2026-08-04T02:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DdfHxZciCa6OG/DcLGWlKk/3V7/esTEP3vdT/OZCK6xeHEuXD0g6OfeS/5bEwQoSTRpXYkCO9EvmhqjFYMW5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:51:58.055283Z"},"content_sha256":"d343c5d6ce0705a605da77e45b0936781ff60a0cc83b46515f84827e6f034ae0","schema_version":"1.0","event_id":"sha256:d343c5d6ce0705a605da77e45b0936781ff60a0cc83b46515f84827e6f034ae0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FXYI4S4AVLAOJI6TT7TL35ZMC6/bundle.json","state_url":"https://pith.science/pith/FXYI4S4AVLAOJI6TT7TL35ZMC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FXYI4S4AVLAOJI6TT7TL35ZMC6/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":"2026-08-05T20:51:58Z","links":{"resolver":"https://pith.science/pith/FXYI4S4AVLAOJI6TT7TL35ZMC6","bundle":"https://pith.science/pith/FXYI4S4AVLAOJI6TT7TL35ZMC6/bundle.json","state":"https://pith.science/pith/FXYI4S4AVLAOJI6TT7TL35ZMC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FXYI4S4AVLAOJI6TT7TL35ZMC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FXYI4S4AVLAOJI6TT7TL35ZMC6","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":"2e93966efe2c99411f8bd66d1ed46f5c0efcf1d6227c7b630e310cd33d712bcd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-01T11:53:12Z","title_canon_sha256":"a703653387299ec58abc4672403b12dc312f77ef3c705eacef890d66a32593c7"},"schema_version":"1.0","source":{"id":"2604.00787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.00787","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2604.00787v2","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00787","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"FXYI4S4AVLAO","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"FXYI4S4AVLAOJI6T","created_at":"2026-08-04T02:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"FXYI4S4A","created_at":"2026-08-04T02:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:d343c5d6ce0705a605da77e45b0936781ff60a0cc83b46515f84827e6f034ae0","target":"graph","created_at":"2026-08-04T02:09:37Z","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/2604.00787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Mining Software Repositories (MSR) field focuses on analyzing the rich data contained in software repositories to derive actionable insights into software processes and products. Mining repositories at scale requires techniques capable of handling large volumes of heterogeneous data, a challenge for which language models (LMs) are increasingly well-suited. Since the advent of Transformer-based architectures, LMs have been rapidly adopted across a wide range of MSR tasks. This article presents a comprehensive survey of the use of LMs in MSR, based on an analysis of 177 papers. We examine ho","authors_text":"Ana B. S\\'anchez, Miguel Romero-Arjona, Saman Barakat, Sergio Segura","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-01T11:53:12Z","title":"The Rise of Language Models in Mining Software Repositories: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00787","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:bf7fdeeb8ff08a19e6627abf13650b978f58286ed46b6e0e6a801c9706917ba1","target":"record","created_at":"2026-08-04T02:09:37Z","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":"2e93966efe2c99411f8bd66d1ed46f5c0efcf1d6227c7b630e310cd33d712bcd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-01T11:53:12Z","title_canon_sha256":"a703653387299ec58abc4672403b12dc312f77ef3c705eacef890d66a32593c7"},"schema_version":"1.0","source":{"id":"2604.00787","kind":"arxiv","version":2}},"canonical_sha256":"2df08e4b80aac0e4a3d39fe6bdf72c1790dae8103545197d972e841d7b905feb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2df08e4b80aac0e4a3d39fe6bdf72c1790dae8103545197d972e841d7b905feb","first_computed_at":"2026-08-04T02:09:37.002797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:09:37.002797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zlUFXqP+EWXUaIHaRwQZwrRVzJrX8x/b0T3Z1EJfgzkxw2dLBtMt8AOtvnlsB9sPs1qD+YwTp7JpS6a4kcbWBA==","signature_status":"signed_v1","signed_at":"2026-08-04T02:09:37.004749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.00787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf7fdeeb8ff08a19e6627abf13650b978f58286ed46b6e0e6a801c9706917ba1","sha256:d343c5d6ce0705a605da77e45b0936781ff60a0cc83b46515f84827e6f034ae0"],"state_sha256":"67ab59c9a3434726e265d4645f328e9502890971fb9fb438c796198956586f8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qO/vRqJYN/y5s3dyNYIHPXkthktTCro3va5NK5C2IgelVZX6OatWcIMowByeja+xlfIs6KlWgWHjOPsE+61zDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:51:58.059338Z","bundle_sha256":"a3ef8f6ab2c3d82045ade2e3f383cc4881cae518795cb8d5e3f55d7857c5da62"}}