{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MEDSR5FUPAAYVD7HV3QD6WLI7O","short_pith_number":"pith:MEDSR5FU","canonical_record":{"source":{"id":"2212.09976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T03:39:24Z","cross_cats_sorted":[],"title_canon_sha256":"836a4f5102a7440e2f754566bc169c374da682604ea72399b11938080b51261a","abstract_canon_sha256":"54ac9551287ef2e89d201473ac87cf95939ea330b33b2efe90823369e25d5ca8"},"schema_version":"1.0"},"canonical_sha256":"610728f4b478018a8fe7aee03f5968fbadc2a0abf8eee283e2aacd25642b6f72","source":{"kind":"arxiv","id":"2212.09976","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09976","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09976v1","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09976","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"MEDSR5FUPAAY","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"MEDSR5FUPAAYVD7H","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"MEDSR5FU","created_at":"2026-07-05T05:27:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MEDSR5FUPAAYVD7HV3QD6WLI7O","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T03:39:24Z","cross_cats_sorted":[],"title_canon_sha256":"836a4f5102a7440e2f754566bc169c374da682604ea72399b11938080b51261a","abstract_canon_sha256":"54ac9551287ef2e89d201473ac87cf95939ea330b33b2efe90823369e25d5ca8"},"schema_version":"1.0"},"canonical_sha256":"610728f4b478018a8fe7aee03f5968fbadc2a0abf8eee283e2aacd25642b6f72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:02.315016Z","signature_b64":"ck3rcQs2Jv1wNDJUNwwqd6ERML4Na4oSCaygOGv5gtiFqmUTwGXfKbNw2Rd5Ne68fZ4G4lz7fe26uGoztUUUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"610728f4b478018a8fe7aee03f5968fbadc2a0abf8eee283e2aacd25642b6f72","last_reissued_at":"2026-07-05T05:27:02.314631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:02.314631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09976","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":"2026-07-05T05:27:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/pULjmGk8WPrdTuAJ40yCOhUVi/dZAZBVSL+lxhqgYtuGI2eXzUPdpzsa/K9SVjH6RwmK02RkNV//7CH3SZzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:26:57.218689Z"},"content_sha256":"1ed1b883c1d147b5aab13ae2d47eebd9173bbcaa689bee2d348f948007c028cd","schema_version":"1.0","event_id":"sha256:1ed1b883c1d147b5aab13ae2d47eebd9173bbcaa689bee2d348f948007c028cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MEDSR5FUPAAYVD7HV3QD6WLI7O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding the Impacts of Textual Dissimilarity on Duplicate Bug Report Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mohammad Masudur Rahman, Sigma Jahan","submitted_at":"2022-12-20T03:39:24Z","abstract_excerpt":"About 40% of software bug reports are duplicates of one another, which pose a major overhead during software maintenance. Traditional techniques often focus on detecting duplicate bug reports that are textually similar. However, in bug tracking systems, many duplicate bug reports might not be textually similar, for which the traditional techniques might fall short. In this paper, we conduct a large-scale empirical study to better understand the impacts of textual dissimilarity on the detection of duplicate bug reports. First, we collect a total of 92,854 bug reports from three open-source syst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09976","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.09976/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":"2026-07-05T05:27:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wa3o6gEkMv5lzc8KtPRE6vABFblxsf/3NGaL3I/nWad+VCauWf35V6fMPSuMkoHSx2UKmfx4+nUZyZ02sHZUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:26:57.219189Z"},"content_sha256":"b2b79f4ac3515a82a99f20771391323af27492450e96b875dcbae3d6fda04142","schema_version":"1.0","event_id":"sha256:b2b79f4ac3515a82a99f20771391323af27492450e96b875dcbae3d6fda04142"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MEDSR5FUPAAYVD7HV3QD6WLI7O/bundle.json","state_url":"https://pith.science/pith/MEDSR5FUPAAYVD7HV3QD6WLI7O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MEDSR5FUPAAYVD7HV3QD6WLI7O/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":"2026-08-14T19:26:57Z","links":{"resolver":"https://pith.science/pith/MEDSR5FUPAAYVD7HV3QD6WLI7O","bundle":"https://pith.science/pith/MEDSR5FUPAAYVD7HV3QD6WLI7O/bundle.json","state":"https://pith.science/pith/MEDSR5FUPAAYVD7HV3QD6WLI7O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MEDSR5FUPAAYVD7HV3QD6WLI7O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MEDSR5FUPAAYVD7HV3QD6WLI7O","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":"54ac9551287ef2e89d201473ac87cf95939ea330b33b2efe90823369e25d5ca8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T03:39:24Z","title_canon_sha256":"836a4f5102a7440e2f754566bc169c374da682604ea72399b11938080b51261a"},"schema_version":"1.0","source":{"id":"2212.09976","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09976","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09976v1","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09976","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"MEDSR5FUPAAY","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"MEDSR5FUPAAYVD7H","created_at":"2026-07-05T05:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"MEDSR5FU","created_at":"2026-07-05T05:27:02Z"}],"graph_snapshots":[{"event_id":"sha256:b2b79f4ac3515a82a99f20771391323af27492450e96b875dcbae3d6fda04142","target":"graph","created_at":"2026-07-05T05:27:02Z","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/2212.09976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"About 40% of software bug reports are duplicates of one another, which pose a major overhead during software maintenance. Traditional techniques often focus on detecting duplicate bug reports that are textually similar. However, in bug tracking systems, many duplicate bug reports might not be textually similar, for which the traditional techniques might fall short. In this paper, we conduct a large-scale empirical study to better understand the impacts of textual dissimilarity on the detection of duplicate bug reports. First, we collect a total of 92,854 bug reports from three open-source syst","authors_text":"Mohammad Masudur Rahman, Sigma Jahan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T03:39:24Z","title":"Towards Understanding the Impacts of Textual Dissimilarity on Duplicate Bug Report Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09976","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":"sha256:1ed1b883c1d147b5aab13ae2d47eebd9173bbcaa689bee2d348f948007c028cd","target":"record","created_at":"2026-07-05T05:27:02Z","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":"54ac9551287ef2e89d201473ac87cf95939ea330b33b2efe90823369e25d5ca8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T03:39:24Z","title_canon_sha256":"836a4f5102a7440e2f754566bc169c374da682604ea72399b11938080b51261a"},"schema_version":"1.0","source":{"id":"2212.09976","kind":"arxiv","version":1}},"canonical_sha256":"610728f4b478018a8fe7aee03f5968fbadc2a0abf8eee283e2aacd25642b6f72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"610728f4b478018a8fe7aee03f5968fbadc2a0abf8eee283e2aacd25642b6f72","first_computed_at":"2026-07-05T05:27:02.314631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:02.314631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ck3rcQs2Jv1wNDJUNwwqd6ERML4Na4oSCaygOGv5gtiFqmUTwGXfKbNw2Rd5Ne68fZ4G4lz7fe26uGoztUUUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:02.315016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09976","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ed1b883c1d147b5aab13ae2d47eebd9173bbcaa689bee2d348f948007c028cd","sha256:b2b79f4ac3515a82a99f20771391323af27492450e96b875dcbae3d6fda04142"],"state_sha256":"2fdb41ba01e9835344c2ec981546f6c68fc329d79285e550fa613c431f0a3ae0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9p2756UcdBHxp0J2mOIhrKWUy2kaYvKJIAJ2TInt1dWd2fVjpWbbkDozoU+7An9kVd+aIId1Xkmm7w8XNpvvDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:26:57.224479Z","bundle_sha256":"b6dc0f1a3d156f89486cd857234b8ed7cc598729c68a79dbe546c10c3b5f6df5"}}