{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HJ2GVRT3N2WXBU52MJG3KNAKHG","short_pith_number":"pith:HJ2GVRT3","schema_version":"1.0","canonical_sha256":"3a746ac67b6ead70d3ba624db5340a3990bd9c34d955f56f841136391263cf2f","source":{"kind":"arxiv","id":"2004.08178","version":5},"attestation_state":"computed","paper":{"title":"Highway Transformer: Self-Gating Enhanced Self-Attentive Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shuo Jin, Xinwen Hou, Yekun Chai","submitted_at":"2020-04-17T11:25:07Z","abstract_excerpt":"Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, standing on the multi-headed dot product attention by attending to all the global contexts at different locations. Through a pseudo information highway, we introduce a gated component self-dependency units (SDU) that incorporates LSTM-styled gating units to replenish internal semantic importance within the multi-dimensional latent space of individual representations. The subsidiary content-based SDU gates allow for the information flow of modulated latent embeddings through skipped"},"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":"2004.08178","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-17T11:25:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"67a170e9a3e725716eba0f2107ebbf1990acfcb00631d6655df7c92b60413607","abstract_canon_sha256":"d92226c1cbdf92a3fd64216c58e454c77005cad3c3fcb3f42899f505161bcd92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:49.552524Z","signature_b64":"+LwwuTz5NvTydOHaThOncDn4eKR/40GAgm4YxX+1OUcapYHsJJfFfFbB8Ui5Ts5+v8QpmQqBW2B8rAb7l3o1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a746ac67b6ead70d3ba624db5340a3990bd9c34d955f56f841136391263cf2f","last_reissued_at":"2026-07-05T01:53:49.552033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:49.552033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Highway Transformer: Self-Gating Enhanced Self-Attentive Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shuo Jin, Xinwen Hou, Yekun Chai","submitted_at":"2020-04-17T11:25:07Z","abstract_excerpt":"Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, standing on the multi-headed dot product attention by attending to all the global contexts at different locations. Through a pseudo information highway, we introduce a gated component self-dependency units (SDU) that incorporates LSTM-styled gating units to replenish internal semantic importance within the multi-dimensional latent space of individual representations. The subsidiary content-based SDU gates allow for the information flow of modulated latent embeddings through skipped"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08178","kind":"arxiv","version":5},"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/2004.08178/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.08178","created_at":"2026-07-05T01:53:49.552090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.08178v5","created_at":"2026-07-05T01:53:49.552090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08178","created_at":"2026-07-05T01:53:49.552090+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJ2GVRT3N2WX","created_at":"2026-07-05T01:53:49.552090+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJ2GVRT3N2WXBU52","created_at":"2026-07-05T01:53:49.552090+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJ2GVRT3","created_at":"2026-07-05T01:53:49.552090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09852","citing_title":"InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG","json":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG.json","graph_json":"https://pith.science/api/pith-number/HJ2GVRT3N2WXBU52MJG3KNAKHG/graph.json","events_json":"https://pith.science/api/pith-number/HJ2GVRT3N2WXBU52MJG3KNAKHG/events.json","paper":"https://pith.science/paper/HJ2GVRT3"},"agent_actions":{"view_html":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG","download_json":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG.json","view_paper":"https://pith.science/paper/HJ2GVRT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.08178&json=true","fetch_graph":"https://pith.science/api/pith-number/HJ2GVRT3N2WXBU52MJG3KNAKHG/graph.json","fetch_events":"https://pith.science/api/pith-number/HJ2GVRT3N2WXBU52MJG3KNAKHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG/action/storage_attestation","attest_author":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG/action/author_attestation","sign_citation":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG/action/citation_signature","submit_replication":"https://pith.science/pith/HJ2GVRT3N2WXBU52MJG3KNAKHG/action/replication_record"}},"created_at":"2026-07-05T01:53:49.552090+00:00","updated_at":"2026-07-05T01:53:49.552090+00:00"}