{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RET4E2TGUF24DR6ALZS2GDSR2P","short_pith_number":"pith:RET4E2TG","canonical_record":{"source":{"id":"2308.09193","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-17T21:36:56Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2675609f54ff2af15eb7bbac71fd513833142509ba4d426900e20e79d00988f7","abstract_canon_sha256":"b33a43bcda4abe5bc7e2374710d68dc9ac3e5f8789055adbf238f3bee637a40a"},"schema_version":"1.0"},"canonical_sha256":"8927c26a66a175c1c7c05e65a30e51d3fcb8ee9ebc677abe93cee1d2eed63948","source":{"kind":"arxiv","id":"2308.09193","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09193","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09193v2","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09193","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"RET4E2TGUF24","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"RET4E2TGUF24DR6A","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"RET4E2TG","created_at":"2026-07-05T07:18:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RET4E2TGUF24DR6ALZS2GDSR2P","target":"record","payload":{"canonical_record":{"source":{"id":"2308.09193","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-17T21:36:56Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2675609f54ff2af15eb7bbac71fd513833142509ba4d426900e20e79d00988f7","abstract_canon_sha256":"b33a43bcda4abe5bc7e2374710d68dc9ac3e5f8789055adbf238f3bee637a40a"},"schema_version":"1.0"},"canonical_sha256":"8927c26a66a175c1c7c05e65a30e51d3fcb8ee9ebc677abe93cee1d2eed63948","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:59.937728Z","signature_b64":"GztYq7eunVh94fJcijP6jr91kD/Mclb1Uf341RVuVMKeKBa/72koSASZzfWDRuOj7ybaJn1eZhtxC4RfD2w8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8927c26a66a175c1c7c05e65a30e51d3fcb8ee9ebc677abe93cee1d2eed63948","last_reissued_at":"2026-07-05T07:18:59.937281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:59.937281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.09193","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":"2026-07-05T07:18:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QzGokTPNc6tTRMXaC/fJy/IsgU1K7uFaInH2B70DKVMwRSF+S66M2dYLBF7zwNGSUrS0g06kNYGwBX74HrH+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T19:52:45.136882Z"},"content_sha256":"22f08784c974c36c04f7d2278fd2fff23c70f31a8cf42047627686cc3b51c1ba","schema_version":"1.0","event_id":"sha256:22f08784c974c36c04f7d2278fd2fff23c70f31a8cf42047627686cc3b51c1ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RET4E2TGUF24DR6ALZS2GDSR2P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of Text Embedding Models for Semantic Text Similarity in Bug Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Aryan Jadon, Avinash Patil, Kihwan Han","submitted_at":"2023-08-17T21:36:56Z","abstract_excerpt":"Bug reports are an essential aspect of software development, and it is crucial to identify and resolve them quickly to ensure the consistent functioning of software systems. Retrieving similar bug reports from an existing database can help reduce the time and effort required to resolve bugs. In this paper, we compared the effectiveness of semantic textual similarity methods for retrieving similar bug reports based on a similarity score. We explored several embedding models such as TF-IDF (Baseline), FastText, Gensim, BERT, and ADA. We used the Software Defects Data containing bug reports for v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09193","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/2308.09193/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":"2026-07-05T07:18:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wcsOMEaklrEXo13DUg9GZx5hH/mL/v5ajwWHiF6+y7eva6M/0wynCZAswwL3yRQ0bG3eS0vQQsoE1wl+8raeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T19:52:45.137484Z"},"content_sha256":"652f83ef8887de0948e64a87c15f03b2a607995df5628a2720073cd0274d9c61","schema_version":"1.0","event_id":"sha256:652f83ef8887de0948e64a87c15f03b2a607995df5628a2720073cd0274d9c61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RET4E2TGUF24DR6ALZS2GDSR2P/bundle.json","state_url":"https://pith.science/pith/RET4E2TGUF24DR6ALZS2GDSR2P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RET4E2TGUF24DR6ALZS2GDSR2P/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":"2026-08-02T19:52:45Z","links":{"resolver":"https://pith.science/pith/RET4E2TGUF24DR6ALZS2GDSR2P","bundle":"https://pith.science/pith/RET4E2TGUF24DR6ALZS2GDSR2P/bundle.json","state":"https://pith.science/pith/RET4E2TGUF24DR6ALZS2GDSR2P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RET4E2TGUF24DR6ALZS2GDSR2P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RET4E2TGUF24DR6ALZS2GDSR2P","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":"b33a43bcda4abe5bc7e2374710d68dc9ac3e5f8789055adbf238f3bee637a40a","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-17T21:36:56Z","title_canon_sha256":"2675609f54ff2af15eb7bbac71fd513833142509ba4d426900e20e79d00988f7"},"schema_version":"1.0","source":{"id":"2308.09193","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09193","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09193v2","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09193","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"RET4E2TGUF24","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"RET4E2TGUF24DR6A","created_at":"2026-07-05T07:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"RET4E2TG","created_at":"2026-07-05T07:18:59Z"}],"graph_snapshots":[{"event_id":"sha256:652f83ef8887de0948e64a87c15f03b2a607995df5628a2720073cd0274d9c61","target":"graph","created_at":"2026-07-05T07:18:59Z","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/2308.09193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bug reports are an essential aspect of software development, and it is crucial to identify and resolve them quickly to ensure the consistent functioning of software systems. Retrieving similar bug reports from an existing database can help reduce the time and effort required to resolve bugs. In this paper, we compared the effectiveness of semantic textual similarity methods for retrieving similar bug reports based on a similarity score. We explored several embedding models such as TF-IDF (Baseline), FastText, Gensim, BERT, and ADA. We used the Software Defects Data containing bug reports for v","authors_text":"Aryan Jadon, Avinash Patil, Kihwan Han","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-17T21:36:56Z","title":"A Comparative Study of Text Embedding Models for Semantic Text Similarity in Bug Reports"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09193","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":"sha256:22f08784c974c36c04f7d2278fd2fff23c70f31a8cf42047627686cc3b51c1ba","target":"record","created_at":"2026-07-05T07:18:59Z","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":"b33a43bcda4abe5bc7e2374710d68dc9ac3e5f8789055adbf238f3bee637a40a","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-17T21:36:56Z","title_canon_sha256":"2675609f54ff2af15eb7bbac71fd513833142509ba4d426900e20e79d00988f7"},"schema_version":"1.0","source":{"id":"2308.09193","kind":"arxiv","version":2}},"canonical_sha256":"8927c26a66a175c1c7c05e65a30e51d3fcb8ee9ebc677abe93cee1d2eed63948","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8927c26a66a175c1c7c05e65a30e51d3fcb8ee9ebc677abe93cee1d2eed63948","first_computed_at":"2026-07-05T07:18:59.937281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:59.937281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GztYq7eunVh94fJcijP6jr91kD/Mclb1Uf341RVuVMKeKBa/72koSASZzfWDRuOj7ybaJn1eZhtxC4RfD2w8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:59.937728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09193","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22f08784c974c36c04f7d2278fd2fff23c70f31a8cf42047627686cc3b51c1ba","sha256:652f83ef8887de0948e64a87c15f03b2a607995df5628a2720073cd0274d9c61"],"state_sha256":"cd86b2a399ae2e3e11d44bf851eb80e2d93e4ec41797619a294f3774a02ddc95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/bKH1qe/R5V0lPOzvsH9Em54tiZVhjEyoDR8w7Q1WCPswhKDiGl4WUPJLmNdkAr5pDvzY7VQjZ2bN2i5/hVyBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T19:52:45.142825Z","bundle_sha256":"5289728e3d6a97e81fd42c8f1300f78cb5399df0106013414db55b21685f4149"}}