{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:47ER53HNHMX7RN3F3OJ3EVOXTK","short_pith_number":"pith:47ER53HN","schema_version":"1.0","canonical_sha256":"e7c91eeced3b2ff8b765db93b255d79a993cc9c457163f1e5c6934a0d9de56a1","source":{"kind":"arxiv","id":"2111.06599","version":1},"attestation_state":"computed","paper":{"title":"PESTO: Switching Point based Dynamic and Relative Positional Encoding for Code-Mixed Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amitava Das, Kandukuri Sai Teja, Mohsin Ali, Parth Patwa, Sumanth Manduru","submitted_at":"2021-11-12T08:18:21Z","abstract_excerpt":"NLP applications for code-mixed (CM) or mix-lingual text have gained a significant momentum recently, the main reason being the prevalence of language mixing in social media communications in multi-lingual societies like India, Mexico, Europe, parts of USA etc. Word embeddings are basic build-ing blocks of any NLP system today, yet, word embedding for CM languages is an unexplored territory. The major bottleneck for CM word embeddings is switching points, where the language switches. These locations lack in contextually and statistical systems fail to model this phenomena due to high variance "},"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":"2111.06599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-12T08:18:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d84cf5f5a22f18d3d998522366c1d6abe6fbb61e38384fa7a65126bad6ffb610","abstract_canon_sha256":"e3fc8a783dbd4c413a12e5cb64e1163b1cc55c6263ac2f3a578fd409a93ca6cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:15.556848Z","signature_b64":"30bU+10wKG42oop1EHVHJUtCPyIRoQGvZ9YGdKyQ87DL33RoFvEuYaLGYpXYjJm/XCADBFGoA/pf/nRnRKNwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7c91eeced3b2ff8b765db93b255d79a993cc9c457163f1e5c6934a0d9de56a1","last_reissued_at":"2026-07-05T03:31:15.556405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:15.556405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PESTO: Switching Point based Dynamic and Relative Positional Encoding for Code-Mixed Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amitava Das, Kandukuri Sai Teja, Mohsin Ali, Parth Patwa, Sumanth Manduru","submitted_at":"2021-11-12T08:18:21Z","abstract_excerpt":"NLP applications for code-mixed (CM) or mix-lingual text have gained a significant momentum recently, the main reason being the prevalence of language mixing in social media communications in multi-lingual societies like India, Mexico, Europe, parts of USA etc. Word embeddings are basic build-ing blocks of any NLP system today, yet, word embedding for CM languages is an unexplored territory. The major bottleneck for CM word embeddings is switching points, where the language switches. These locations lack in contextually and statistical systems fail to model this phenomena due to high variance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06599","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/2111.06599/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":"2111.06599","created_at":"2026-07-05T03:31:15.556486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.06599v1","created_at":"2026-07-05T03:31:15.556486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06599","created_at":"2026-07-05T03:31:15.556486+00:00"},{"alias_kind":"pith_short_12","alias_value":"47ER53HNHMX7","created_at":"2026-07-05T03:31:15.556486+00:00"},{"alias_kind":"pith_short_16","alias_value":"47ER53HNHMX7RN3F","created_at":"2026-07-05T03:31:15.556486+00:00"},{"alias_kind":"pith_short_8","alias_value":"47ER53HN","created_at":"2026-07-05T03:31:15.556486+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/47ER53HNHMX7RN3F3OJ3EVOXTK","json":"https://pith.science/pith/47ER53HNHMX7RN3F3OJ3EVOXTK.json","graph_json":"https://pith.science/api/pith-number/47ER53HNHMX7RN3F3OJ3EVOXTK/graph.json","events_json":"https://pith.science/api/pith-number/47ER53HNHMX7RN3F3OJ3EVOXTK/events.json","paper":"https://pith.science/paper/47ER53HN"},"agent_actions":{"view_html":"https://pith.science/pith/47ER53HNHMX7RN3F3OJ3EVOXTK","download_json":"https://pith.science/pith/47ER53HNHMX7RN3F3OJ3EVOXTK.json","view_paper":"https://pith.science/paper/47ER53HN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.06599&json=true","fetch_graph":"https://pith.science/api/pith-number/47ER53HNHMX7RN3F3OJ3EVOXTK/graph.json","fetch_events":"https://pith.science/api/pith-number/47ER53HNHMX7RN3F3OJ3EVOXTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47ER53HNHMX7RN3F3OJ3EVOXTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47ER53HNHMX7RN3F3OJ3EVOXTK/action/storage_attestation","attest_author":"https://pith.science/pith/47ER53HNHMX7RN3F3OJ3EVOXTK/action/author_attestation","sign_citation":"https://pith.science/pith/47ER53HNHMX7RN3F3OJ3EVOXTK/action/citation_signature","submit_replication":"https://pith.science/pith/47ER53HNHMX7RN3F3OJ3EVOXTK/action/replication_record"}},"created_at":"2026-07-05T03:31:15.556486+00:00","updated_at":"2026-07-05T03:31:15.556486+00:00"}