{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PPB5QJ2URCIPHBW5SOS4Z63CAM","short_pith_number":"pith:PPB5QJ2U","canonical_record":{"source":{"id":"2007.02599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-07-06T09:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"afa1d9f9c3000cb34d70b6b8ca10747df37204c7cab1d322d108d6776df5b013","abstract_canon_sha256":"fe0621e84178b62226d57aa52880b2ed0ce39c90874b29b4058a3de3c13c685a"},"schema_version":"1.0"},"canonical_sha256":"7bc3d827548890f386dd93a5ccfb6203052ef6bfc4856f0c90fbc00bc56fcd4e","source":{"kind":"arxiv","id":"2007.02599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02599","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02599v1","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02599","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"pith_short_12","alias_value":"PPB5QJ2URCIP","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"pith_short_16","alias_value":"PPB5QJ2URCIPHBW5","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"pith_short_8","alias_value":"PPB5QJ2U","created_at":"2026-07-05T01:16:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PPB5QJ2URCIPHBW5SOS4Z63CAM","target":"record","payload":{"canonical_record":{"source":{"id":"2007.02599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-07-06T09:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"afa1d9f9c3000cb34d70b6b8ca10747df37204c7cab1d322d108d6776df5b013","abstract_canon_sha256":"fe0621e84178b62226d57aa52880b2ed0ce39c90874b29b4058a3de3c13c685a"},"schema_version":"1.0"},"canonical_sha256":"7bc3d827548890f386dd93a5ccfb6203052ef6bfc4856f0c90fbc00bc56fcd4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:23.550513Z","signature_b64":"/izqkU1/vov6a7Wdt9dRzOURf6qhVM7YyDMbYTwPMRqXugVUWzhdTUexaa//ttreWuRaPF8RsylH7JmO4sHZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bc3d827548890f386dd93a5ccfb6203052ef6bfc4856f0c90fbc00bc56fcd4e","last_reissued_at":"2026-07-05T01:16:23.550084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:23.550084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.02599","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":"2026-07-05T01:16:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nvNVwTN2Dc4dG+WEzKmED8JU7q2j5noR1O8+cxD5GqAWKJvU98uPmV7nIkXzN7WPh5P6YCYNcMEpfQmKsn3/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:19:53.272365Z"},"content_sha256":"ac12487af18af9ce8efdbb34a55c20242f0c5789187ce17de05d954c878754e9","schema_version":"1.0","event_id":"sha256:ac12487af18af9ce8efdbb34a55c20242f0c5789187ce17de05d954c878754e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PPB5QJ2URCIPHBW5SOS4Z63CAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sosed: a tool for finding similar software projects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Artyom Lobanov, Egor Bogomolov, Timofey Bryksin, Vladimir Kovalenko, Yaroslav Golubev","submitted_at":"2020-07-06T09:18:20Z","abstract_excerpt":"In this paper, we present Sosed, a tool for discovering similar software projects. We use fastText to compute the embeddings of subtokens into a dense space for 120,000 GitHub repositories in 200 languages. Then, we cluster embeddings to identify groups of semantically similar sub-tokens that reflect topics in source code. We use a dataset of 9 million GitHub projects as a reference search base. To identify similar projects, we compare the distributions of clusters among their sub-tokens. The tool receives an arbitrary project as input, extracts sub-tokens in 16 most popular programming langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02599","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/2007.02599/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":"2026-07-05T01:16:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgFijgGtyp39ld5EL7p5mwtLrxiQiZSPsCOP6LgoWz1Z+8eETfAjNYyyT6QPKGlv8UDifMf+D+orq/tMxbQECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:19:53.272748Z"},"content_sha256":"03b6ab503ceace091601a73f225968847bb23d528f6d61152d90a6534822f40f","schema_version":"1.0","event_id":"sha256:03b6ab503ceace091601a73f225968847bb23d528f6d61152d90a6534822f40f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPB5QJ2URCIPHBW5SOS4Z63CAM/bundle.json","state_url":"https://pith.science/pith/PPB5QJ2URCIPHBW5SOS4Z63CAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPB5QJ2URCIPHBW5SOS4Z63CAM/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":"2026-07-06T16:19:53Z","links":{"resolver":"https://pith.science/pith/PPB5QJ2URCIPHBW5SOS4Z63CAM","bundle":"https://pith.science/pith/PPB5QJ2URCIPHBW5SOS4Z63CAM/bundle.json","state":"https://pith.science/pith/PPB5QJ2URCIPHBW5SOS4Z63CAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPB5QJ2URCIPHBW5SOS4Z63CAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PPB5QJ2URCIPHBW5SOS4Z63CAM","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":"fe0621e84178b62226d57aa52880b2ed0ce39c90874b29b4058a3de3c13c685a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-07-06T09:18:20Z","title_canon_sha256":"afa1d9f9c3000cb34d70b6b8ca10747df37204c7cab1d322d108d6776df5b013"},"schema_version":"1.0","source":{"id":"2007.02599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02599","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02599v1","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02599","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"pith_short_12","alias_value":"PPB5QJ2URCIP","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"pith_short_16","alias_value":"PPB5QJ2URCIPHBW5","created_at":"2026-07-05T01:16:23Z"},{"alias_kind":"pith_short_8","alias_value":"PPB5QJ2U","created_at":"2026-07-05T01:16:23Z"}],"graph_snapshots":[{"event_id":"sha256:03b6ab503ceace091601a73f225968847bb23d528f6d61152d90a6534822f40f","target":"graph","created_at":"2026-07-05T01:16:23Z","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/2007.02599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present Sosed, a tool for discovering similar software projects. We use fastText to compute the embeddings of subtokens into a dense space for 120,000 GitHub repositories in 200 languages. Then, we cluster embeddings to identify groups of semantically similar sub-tokens that reflect topics in source code. We use a dataset of 9 million GitHub projects as a reference search base. To identify similar projects, we compare the distributions of clusters among their sub-tokens. The tool receives an arbitrary project as input, extracts sub-tokens in 16 most popular programming langua","authors_text":"Artyom Lobanov, Egor Bogomolov, Timofey Bryksin, Vladimir Kovalenko, Yaroslav Golubev","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-07-06T09:18:20Z","title":"Sosed: a tool for finding similar software projects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02599","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:ac12487af18af9ce8efdbb34a55c20242f0c5789187ce17de05d954c878754e9","target":"record","created_at":"2026-07-05T01:16:23Z","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":"fe0621e84178b62226d57aa52880b2ed0ce39c90874b29b4058a3de3c13c685a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-07-06T09:18:20Z","title_canon_sha256":"afa1d9f9c3000cb34d70b6b8ca10747df37204c7cab1d322d108d6776df5b013"},"schema_version":"1.0","source":{"id":"2007.02599","kind":"arxiv","version":1}},"canonical_sha256":"7bc3d827548890f386dd93a5ccfb6203052ef6bfc4856f0c90fbc00bc56fcd4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bc3d827548890f386dd93a5ccfb6203052ef6bfc4856f0c90fbc00bc56fcd4e","first_computed_at":"2026-07-05T01:16:23.550084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:23.550084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/izqkU1/vov6a7Wdt9dRzOURf6qhVM7YyDMbYTwPMRqXugVUWzhdTUexaa//ttreWuRaPF8RsylH7JmO4sHZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:23.550513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.02599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac12487af18af9ce8efdbb34a55c20242f0c5789187ce17de05d954c878754e9","sha256:03b6ab503ceace091601a73f225968847bb23d528f6d61152d90a6534822f40f"],"state_sha256":"99d917e3a7ff07ed11bc96ed6ea820d9ef86ff8f2f7e06a22bdf7e816201cbe1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4z5WaCsTtquWaCfVVRSo0l06FaYN4YRpkxk/Q2IW0UBgr9ecZvvb2MtTWwqrYpHymeULVZS7/+/UlzFCemt+BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:19:53.274736Z","bundle_sha256":"4ddc3befe9a38c6aefc6544d5bafb855ded43688331cf197f5a408e13400ec8c"}}