{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WEPYVXFA6RTK53MLH5MWPLFLTX","short_pith_number":"pith:WEPYVXFA","schema_version":"1.0","canonical_sha256":"b11f8adca0f466aeed8b3f5967acab9dc51ecdb79b26a9f8821ae594845ec142","source":{"kind":"arxiv","id":"1911.12864","version":1},"attestation_state":"computed","paper":{"title":"Self-attention with Functional Time Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuanwei Ruan, Da Xu, Evren Korpeoglu, Kannan Achan, Sushant Kumar","submitted_at":"2019-11-28T21:04:21Z","abstract_excerpt":"Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and interpretability, self-attention is gradually becoming a key component in event sequence models. However, like most other sequence models, self-attention does not account for the time span between events and thus captures sequential signals rather than temporal patterns. Without relying on recurrent network structures, self-attention recognizes event orderings via positional encoding. To bridge the gap between modelling"},"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":"1911.12864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-28T21:04:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e5e220cc3e9fa7636c7bb72326161daa2f349c1df04dcce87c903e64fd2fe92c","abstract_canon_sha256":"45e615c929aee3b22dd3edb7cd2cda3c74716bfd5adb0ffec60936082893b4e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:49.721472Z","signature_b64":"LvvnNgoQOq6hFU+n5UenHKqb+fENGtWM1wpbYunsqsJVjoH+BaAO5op45BweYAfyu0kqqSIkPiZBX4tHHSZ2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b11f8adca0f466aeed8b3f5967acab9dc51ecdb79b26a9f8821ae594845ec142","last_reissued_at":"2026-07-05T00:22:49.721051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:49.721051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-attention with Functional Time Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuanwei Ruan, Da Xu, Evren Korpeoglu, Kannan Achan, Sushant Kumar","submitted_at":"2019-11-28T21:04:21Z","abstract_excerpt":"Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and interpretability, self-attention is gradually becoming a key component in event sequence models. However, like most other sequence models, self-attention does not account for the time span between events and thus captures sequential signals rather than temporal patterns. Without relying on recurrent network structures, self-attention recognizes event orderings via positional encoding. To bridge the gap between modelling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12864","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/1911.12864/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":"1911.12864","created_at":"2026-07-05T00:22:49.721111+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.12864v1","created_at":"2026-07-05T00:22:49.721111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12864","created_at":"2026-07-05T00:22:49.721111+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEPYVXFA6RTK","created_at":"2026-07-05T00:22:49.721111+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEPYVXFA6RTK53ML","created_at":"2026-07-05T00:22:49.721111+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEPYVXFA","created_at":"2026-07-05T00:22:49.721111+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/WEPYVXFA6RTK53MLH5MWPLFLTX","json":"https://pith.science/pith/WEPYVXFA6RTK53MLH5MWPLFLTX.json","graph_json":"https://pith.science/api/pith-number/WEPYVXFA6RTK53MLH5MWPLFLTX/graph.json","events_json":"https://pith.science/api/pith-number/WEPYVXFA6RTK53MLH5MWPLFLTX/events.json","paper":"https://pith.science/paper/WEPYVXFA"},"agent_actions":{"view_html":"https://pith.science/pith/WEPYVXFA6RTK53MLH5MWPLFLTX","download_json":"https://pith.science/pith/WEPYVXFA6RTK53MLH5MWPLFLTX.json","view_paper":"https://pith.science/paper/WEPYVXFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.12864&json=true","fetch_graph":"https://pith.science/api/pith-number/WEPYVXFA6RTK53MLH5MWPLFLTX/graph.json","fetch_events":"https://pith.science/api/pith-number/WEPYVXFA6RTK53MLH5MWPLFLTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEPYVXFA6RTK53MLH5MWPLFLTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEPYVXFA6RTK53MLH5MWPLFLTX/action/storage_attestation","attest_author":"https://pith.science/pith/WEPYVXFA6RTK53MLH5MWPLFLTX/action/author_attestation","sign_citation":"https://pith.science/pith/WEPYVXFA6RTK53MLH5MWPLFLTX/action/citation_signature","submit_replication":"https://pith.science/pith/WEPYVXFA6RTK53MLH5MWPLFLTX/action/replication_record"}},"created_at":"2026-07-05T00:22:49.721111+00:00","updated_at":"2026-07-05T00:22:49.721111+00:00"}