{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M7SNJRRT3I5L5C5PIFHKMNTXNQ","short_pith_number":"pith:M7SNJRRT","canonical_record":{"source":{"id":"2305.09608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-05-16T17:00:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"27bbd710c2a9a3acbbc927dfaf3363a56eaf214241f383ed6f7e741de2ca16fc","abstract_canon_sha256":"b0c9506ab7d47cd7bc31cc9245056afc7199d5a241dca9d574e688bceaac1e57"},"schema_version":"1.0"},"canonical_sha256":"67e4d4c633da3abe8baf414ea636776c03d9d220a33c935d092d65daeda175a6","source":{"kind":"arxiv","id":"2305.09608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09608","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09608v1","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09608","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"M7SNJRRT3I5L","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"M7SNJRRT3I5L5C5P","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"M7SNJRRT","created_at":"2026-07-05T06:10:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M7SNJRRT3I5L5C5PIFHKMNTXNQ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.09608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-05-16T17:00:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"27bbd710c2a9a3acbbc927dfaf3363a56eaf214241f383ed6f7e741de2ca16fc","abstract_canon_sha256":"b0c9506ab7d47cd7bc31cc9245056afc7199d5a241dca9d574e688bceaac1e57"},"schema_version":"1.0"},"canonical_sha256":"67e4d4c633da3abe8baf414ea636776c03d9d220a33c935d092d65daeda175a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:49.898112Z","signature_b64":"Xc3UvKTrE8NB9Rq28H7V3ZDamiuNaVdclivyGxK1Vhvvjp75GqZSjXcePDRjDAMwmnxdpSOHp3xqbHRxbwoiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67e4d4c633da3abe8baf414ea636776c03d9d220a33c935d092d65daeda175a6","last_reissued_at":"2026-07-05T06:10:49.897774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:49.897774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.09608","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":"2026-07-05T06:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A72um84GMW0KGdGMETZpOZg5JY5RLF6JvSSXECVCmZmzaegbrclJyjqELe634tUkXzHk4xxpxvQ8hHClK9ZEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:56:45.844642Z"},"content_sha256":"23110ce13b717061c6508a4df807d6d54fdaa7029831a600df428462be591f20","schema_version":"1.0","event_id":"sha256:23110ce13b717061c6508a4df807d6d54fdaa7029831a600df428462be591f20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M7SNJRRT3I5L5C5PIFHKMNTXNQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Augmentation for Conflict and Duplicate Detection in Software Engineering Sentence Pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Ay\\c{s}e Ba\\c{s}ar, Garima Malik, Mucahit Cevik","submitted_at":"2023-05-16T17:00:36Z","abstract_excerpt":"This paper explores the use of text data augmentation techniques to enhance conflict and duplicate detection in software engineering tasks through sentence pair classification. The study adapts generic augmentation techniques such as shuffling, back translation, and paraphrasing and proposes new data augmentation techniques such as Noun-Verb Substitution, target-lemma replacement and Actor-Action Substitution for software requirement texts. A comprehensive empirical analysis is conducted on six software text datasets to identify conflicts and duplicates among sentence pairs. The results demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09608","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/2305.09608/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":"2026-07-05T06:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pl3/pzoehMspGVMtCpqCem5aYdk82JnGxMqQZx7zlexROhCrKOJN2gw3S7xBULgChc1y7udKSYxBh1FhYrzSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:56:45.845170Z"},"content_sha256":"20a7acd5e005a37465b29522a7e99c32abc87aec1a14dec10dd0ab27d9f3b576","schema_version":"1.0","event_id":"sha256:20a7acd5e005a37465b29522a7e99c32abc87aec1a14dec10dd0ab27d9f3b576"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7SNJRRT3I5L5C5PIFHKMNTXNQ/bundle.json","state_url":"https://pith.science/pith/M7SNJRRT3I5L5C5PIFHKMNTXNQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7SNJRRT3I5L5C5PIFHKMNTXNQ/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":"2026-08-17T20:56:45Z","links":{"resolver":"https://pith.science/pith/M7SNJRRT3I5L5C5PIFHKMNTXNQ","bundle":"https://pith.science/pith/M7SNJRRT3I5L5C5PIFHKMNTXNQ/bundle.json","state":"https://pith.science/pith/M7SNJRRT3I5L5C5PIFHKMNTXNQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7SNJRRT3I5L5C5PIFHKMNTXNQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M7SNJRRT3I5L5C5PIFHKMNTXNQ","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":"b0c9506ab7d47cd7bc31cc9245056afc7199d5a241dca9d574e688bceaac1e57","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-05-16T17:00:36Z","title_canon_sha256":"27bbd710c2a9a3acbbc927dfaf3363a56eaf214241f383ed6f7e741de2ca16fc"},"schema_version":"1.0","source":{"id":"2305.09608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09608","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09608v1","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09608","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"M7SNJRRT3I5L","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"M7SNJRRT3I5L5C5P","created_at":"2026-07-05T06:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"M7SNJRRT","created_at":"2026-07-05T06:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:20a7acd5e005a37465b29522a7e99c32abc87aec1a14dec10dd0ab27d9f3b576","target":"graph","created_at":"2026-07-05T06:10:49Z","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/2305.09608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the use of text data augmentation techniques to enhance conflict and duplicate detection in software engineering tasks through sentence pair classification. The study adapts generic augmentation techniques such as shuffling, back translation, and paraphrasing and proposes new data augmentation techniques such as Noun-Verb Substitution, target-lemma replacement and Actor-Action Substitution for software requirement texts. A comprehensive empirical analysis is conducted on six software text datasets to identify conflicts and duplicates among sentence pairs. The results demons","authors_text":"Ay\\c{s}e Ba\\c{s}ar, Garima Malik, Mucahit Cevik","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-05-16T17:00:36Z","title":"Data Augmentation for Conflict and Duplicate Detection in Software Engineering Sentence Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09608","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":"sha256:23110ce13b717061c6508a4df807d6d54fdaa7029831a600df428462be591f20","target":"record","created_at":"2026-07-05T06:10:49Z","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":"b0c9506ab7d47cd7bc31cc9245056afc7199d5a241dca9d574e688bceaac1e57","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-05-16T17:00:36Z","title_canon_sha256":"27bbd710c2a9a3acbbc927dfaf3363a56eaf214241f383ed6f7e741de2ca16fc"},"schema_version":"1.0","source":{"id":"2305.09608","kind":"arxiv","version":1}},"canonical_sha256":"67e4d4c633da3abe8baf414ea636776c03d9d220a33c935d092d65daeda175a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67e4d4c633da3abe8baf414ea636776c03d9d220a33c935d092d65daeda175a6","first_computed_at":"2026-07-05T06:10:49.897774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:10:49.897774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xc3UvKTrE8NB9Rq28H7V3ZDamiuNaVdclivyGxK1Vhvvjp75GqZSjXcePDRjDAMwmnxdpSOHp3xqbHRxbwoiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:10:49.898112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.09608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23110ce13b717061c6508a4df807d6d54fdaa7029831a600df428462be591f20","sha256:20a7acd5e005a37465b29522a7e99c32abc87aec1a14dec10dd0ab27d9f3b576"],"state_sha256":"b2cd082108956f1413d7cef51a48403d30adb71feb30f859583df7d48de63cf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V6JxOVmbhYKnb9n+lqjAladeSkRnRggkO5E2WViBzfk3IYsmteH7qewOBXXlWyoW+HPi7RqTFnQ7HDqBrjA2Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:56:45.854798Z","bundle_sha256":"c90ca3895c1b8940d022c7b934b44948679d6470fdc8899232a0af6da599d43e"}}