{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:FPTBEKYJ54KYVR4U3IOJFWBFIJ","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":"2f9c5dc7fdbc8a7f0bcfdac2d07aa5a853d645568b56ef8f884abd4279d0f721","cross_cats_sorted":["cs.AI","cs.LG","q-bio.GN"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-03-17T17:55:22Z","title_canon_sha256":"5d0f05b08d3f25a95a0fb37fe7e3486a6b2a8859a04db8f234619ebb8515f077"},"schema_version":"1.0","source":{"id":"1503.05140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.05140","created_at":"2026-05-18T01:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"1503.05140v2","created_at":"2026-05-18T01:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.05140","created_at":"2026-05-18T01:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"FPTBEKYJ54KY","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"FPTBEKYJ54KYVR4U","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"FPTBEKYJ","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:b5c5e65326e4cfce3e5ec4a70a9678d0c45d76f737783d0aa7c0abcd52cac84c","target":"graph","created_at":"2026-05-18T01:13:31Z","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":"We introduce a new representation and feature extraction method for biological sequences. Named bio-vectors (BioVec) to refer to biological sequences in general with protein-vectors (ProtVec) for proteins (amino-acid sequences) and gene-vectors (GeneVec) for gene sequences, this representation can be widely used in applications of deep learning in proteomics and genomics. In the present paper, we focus on protein-vectors that can be utilized in a wide array of bioinformatics investigations such as family classification, protein visualization, structure prediction, disordered protein identifica","authors_text":"Ehsaneddin Asgari, Mohammad R.K. Mofrad","cross_cats":["cs.AI","cs.LG","q-bio.GN"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-03-17T17:55:22Z","title":"ProtVec: A Continuous Distributed Representation of Biological Sequences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.05140","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:a32b140ff58fa105d91851764d29284b368db857354ce90ccfa15728df51c289","target":"record","created_at":"2026-05-18T01:13:31Z","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":"2f9c5dc7fdbc8a7f0bcfdac2d07aa5a853d645568b56ef8f884abd4279d0f721","cross_cats_sorted":["cs.AI","cs.LG","q-bio.GN"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-03-17T17:55:22Z","title_canon_sha256":"5d0f05b08d3f25a95a0fb37fe7e3486a6b2a8859a04db8f234619ebb8515f077"},"schema_version":"1.0","source":{"id":"1503.05140","kind":"arxiv","version":2}},"canonical_sha256":"2be6122b09ef158ac794da1c92d8254255188b8ef886f37981e3388f52a1c81e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2be6122b09ef158ac794da1c92d8254255188b8ef886f37981e3388f52a1c81e","first_computed_at":"2026-05-18T01:13:31.024385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:31.024385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o0o1NH2dVDMMZajQQ83O6aHOFNAHV0lot9ODQX7kCXMV1J+D18UPMiJt3EppviSUfoMT03qlgyDpNKDAWDMqBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:31.025296Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.05140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a32b140ff58fa105d91851764d29284b368db857354ce90ccfa15728df51c289","sha256:b5c5e65326e4cfce3e5ec4a70a9678d0c45d76f737783d0aa7c0abcd52cac84c"],"state_sha256":"c3498140f829c69011cf33584197a995a582aaf99f8a6f15e9392d35c6a4a186"}