{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5TD56I7FKVXTS3UHHVQFZ2YNCD","short_pith_number":"pith:5TD56I7F","canonical_record":{"source":{"id":"1907.11817","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2019-07-26T23:28:30Z","cross_cats_sorted":["cs.IR","cs.PL"],"title_canon_sha256":"9c56284629a7126a6cf6aad87de13b943df545f413dd90b8daae38e27df4252f","abstract_canon_sha256":"e18078d606bedb8cfe2bd269418f9e29f077257f6dcadd95891a0b5dfe15ef2b"},"schema_version":"1.0"},"canonical_sha256":"ecc7df23e5556f396e873d605ceb0d10e01cbc1a66ba2579ded42528cbf7b56a","source":{"kind":"arxiv","id":"1907.11817","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11817","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11817v1","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11817","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"5TD56I7FKVXT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5TD56I7FKVXTS3UH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5TD56I7F","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5TD56I7FKVXTS3UHHVQFZ2YNCD","target":"record","payload":{"canonical_record":{"source":{"id":"1907.11817","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2019-07-26T23:28:30Z","cross_cats_sorted":["cs.IR","cs.PL"],"title_canon_sha256":"9c56284629a7126a6cf6aad87de13b943df545f413dd90b8daae38e27df4252f","abstract_canon_sha256":"e18078d606bedb8cfe2bd269418f9e29f077257f6dcadd95891a0b5dfe15ef2b"},"schema_version":"1.0"},"canonical_sha256":"ecc7df23e5556f396e873d605ceb0d10e01cbc1a66ba2579ded42528cbf7b56a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:22.978887Z","signature_b64":"34Ht5nmcUmoBY2KJfTjNuCY2PQdeeGk1ioYx4D6L2wi7zQZNrcpMm2okCis/j49N/38PbG6mUQjSmHguU/MfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecc7df23e5556f396e873d605ceb0d10e01cbc1a66ba2579ded42528cbf7b56a","last_reissued_at":"2026-05-17T23:39:22.978260Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:22.978260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.11817","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":"2026-05-17T23:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IM7zAAoKO9hDI9vBT/cNG0A5RSZ0CaVHbl5vclIQCP5dJdLQoDub4UC8P0gw6kVUl+VJI7U+Jf2/HVVVQEMaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:53:27.566673Z"},"content_sha256":"dd11546543e29d749f662c211057eade819a43cdabc703f74aa037287ec47109","schema_version":"1.0","event_id":"sha256:dd11546543e29d749f662c211057eade819a43cdabc703f74aa037287ec47109"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5TD56I7FKVXTS3UHHVQFZ2YNCD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Source Code Similarity Detection in Large Code Repositories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.PL"],"primary_cat":"cs.SE","authors_text":"F Alomari, M Harbi","submitted_at":"2019-07-26T23:28:30Z","abstract_excerpt":"Source code similarity are increasingly used in application development to identify clones, isolate bugs, and find copy-rights violations. Similar code fragments can be very problematic due to the fact that errors in the original code must be fixed in every copy. Other maintenance changes, such as extensions or patches, must be applied multiple times. Furthermore, the diversity of coding styles and flexibility of modern languages makes it difficult and cost ineffective to manually inspect large code repositories. Therefore, detection is only feasible by automatic techniques. We present an effi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11817","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":"2026-05-17T23:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IptYKUn+9e6pi+EYV4DGzmOJb9eCcp2UC7Nu5llfDSG2BUp5kcZaNkxCQ5aER7dZ4nPm5IW4c2DFjdQSizh1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:53:27.567164Z"},"content_sha256":"9916f11dec8926d2adf9216e74fae3017df02de64879071a582a0c867a42e607","schema_version":"1.0","event_id":"sha256:9916f11dec8926d2adf9216e74fae3017df02de64879071a582a0c867a42e607"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TD56I7FKVXTS3UHHVQFZ2YNCD/bundle.json","state_url":"https://pith.science/pith/5TD56I7FKVXTS3UHHVQFZ2YNCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TD56I7FKVXTS3UHHVQFZ2YNCD/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":"2026-08-11T04:53:27Z","links":{"resolver":"https://pith.science/pith/5TD56I7FKVXTS3UHHVQFZ2YNCD","bundle":"https://pith.science/pith/5TD56I7FKVXTS3UHHVQFZ2YNCD/bundle.json","state":"https://pith.science/pith/5TD56I7FKVXTS3UHHVQFZ2YNCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TD56I7FKVXTS3UHHVQFZ2YNCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5TD56I7FKVXTS3UHHVQFZ2YNCD","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":"e18078d606bedb8cfe2bd269418f9e29f077257f6dcadd95891a0b5dfe15ef2b","cross_cats_sorted":["cs.IR","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2019-07-26T23:28:30Z","title_canon_sha256":"9c56284629a7126a6cf6aad87de13b943df545f413dd90b8daae38e27df4252f"},"schema_version":"1.0","source":{"id":"1907.11817","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11817","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11817v1","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11817","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"5TD56I7FKVXT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5TD56I7FKVXTS3UH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5TD56I7F","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:9916f11dec8926d2adf9216e74fae3017df02de64879071a582a0c867a42e607","target":"graph","created_at":"2026-05-17T23:39:22Z","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 similarity are increasingly used in application development to identify clones, isolate bugs, and find copy-rights violations. Similar code fragments can be very problematic due to the fact that errors in the original code must be fixed in every copy. Other maintenance changes, such as extensions or patches, must be applied multiple times. Furthermore, the diversity of coding styles and flexibility of modern languages makes it difficult and cost ineffective to manually inspect large code repositories. Therefore, detection is only feasible by automatic techniques. We present an effi","authors_text":"F Alomari, M Harbi","cross_cats":["cs.IR","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2019-07-26T23:28:30Z","title":"Scalable Source Code Similarity Detection in Large Code Repositories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11817","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:dd11546543e29d749f662c211057eade819a43cdabc703f74aa037287ec47109","target":"record","created_at":"2026-05-17T23:39:22Z","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":"e18078d606bedb8cfe2bd269418f9e29f077257f6dcadd95891a0b5dfe15ef2b","cross_cats_sorted":["cs.IR","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2019-07-26T23:28:30Z","title_canon_sha256":"9c56284629a7126a6cf6aad87de13b943df545f413dd90b8daae38e27df4252f"},"schema_version":"1.0","source":{"id":"1907.11817","kind":"arxiv","version":1}},"canonical_sha256":"ecc7df23e5556f396e873d605ceb0d10e01cbc1a66ba2579ded42528cbf7b56a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecc7df23e5556f396e873d605ceb0d10e01cbc1a66ba2579ded42528cbf7b56a","first_computed_at":"2026-05-17T23:39:22.978260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:22.978260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"34Ht5nmcUmoBY2KJfTjNuCY2PQdeeGk1ioYx4D6L2wi7zQZNrcpMm2okCis/j49N/38PbG6mUQjSmHguU/MfBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:22.978887Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.11817","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd11546543e29d749f662c211057eade819a43cdabc703f74aa037287ec47109","sha256:9916f11dec8926d2adf9216e74fae3017df02de64879071a582a0c867a42e607"],"state_sha256":"91acba64c0d4380ae3e8665f49d6c6d2ceab19950c17b1e321521021e95d3dc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"voSYxmwEEWy7OE3HMHwRfzT0AwELTfZ5RMRJBWmr+qZo0WCMhBMAyoULB36X14b0BDDz1D9cVaE9gNT6HIRgDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:53:27.571487Z","bundle_sha256":"a0c567da2ae1810b191e305d792f8c539a3c3d984b2e5420a6122cfe4c02cb48"}}