{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:FPTBEKYJ54KYVR4U3IOJFWBFIJ","short_pith_number":"pith:FPTBEKYJ","schema_version":"1.0","canonical_sha256":"2be6122b09ef158ac794da1c92d8254255188b8ef886f37981e3388f52a1c81e","source":{"kind":"arxiv","id":"1503.05140","version":2},"attestation_state":"computed","paper":{"title":"ProtVec: A Continuous Distributed Representation of Biological Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.GN"],"primary_cat":"q-bio.QM","authors_text":"Ehsaneddin Asgari, Mohammad R.K. Mofrad","submitted_at":"2015-03-17T17:55:22Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1503.05140","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-03-17T17:55:22Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.GN"],"title_canon_sha256":"5d0f05b08d3f25a95a0fb37fe7e3486a6b2a8859a04db8f234619ebb8515f077","abstract_canon_sha256":"2f9c5dc7fdbc8a7f0bcfdac2d07aa5a853d645568b56ef8f884abd4279d0f721"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:31.025296Z","signature_b64":"o0o1NH2dVDMMZajQQ83O6aHOFNAHV0lot9ODQX7kCXMV1J+D18UPMiJt3EppviSUfoMT03qlgyDpNKDAWDMqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2be6122b09ef158ac794da1c92d8254255188b8ef886f37981e3388f52a1c81e","last_reissued_at":"2026-05-18T01:13:31.024385Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:31.024385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProtVec: A Continuous Distributed Representation of Biological Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.GN"],"primary_cat":"q-bio.QM","authors_text":"Ehsaneddin Asgari, Mohammad R.K. Mofrad","submitted_at":"2015-03-17T17:55:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.05140","kind":"arxiv","version":2},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1503.05140","created_at":"2026-05-18T01:13:31.024534+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.05140v2","created_at":"2026-05-18T01:13:31.024534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.05140","created_at":"2026-05-18T01:13:31.024534+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPTBEKYJ54KY","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPTBEKYJ54KYVR4U","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPTBEKYJ","created_at":"2026-05-18T12:29:19.899920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ","json":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ.json","graph_json":"https://pith.science/api/pith-number/FPTBEKYJ54KYVR4U3IOJFWBFIJ/graph.json","events_json":"https://pith.science/api/pith-number/FPTBEKYJ54KYVR4U3IOJFWBFIJ/events.json","paper":"https://pith.science/paper/FPTBEKYJ"},"agent_actions":{"view_html":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ","download_json":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ.json","view_paper":"https://pith.science/paper/FPTBEKYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.05140&json=true","fetch_graph":"https://pith.science/api/pith-number/FPTBEKYJ54KYVR4U3IOJFWBFIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FPTBEKYJ54KYVR4U3IOJFWBFIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ/action/storage_attestation","attest_author":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ/action/author_attestation","sign_citation":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ/action/citation_signature","submit_replication":"https://pith.science/pith/FPTBEKYJ54KYVR4U3IOJFWBFIJ/action/replication_record"}},"created_at":"2026-05-18T01:13:31.024534+00:00","updated_at":"2026-05-18T01:13:31.024534+00:00"}