{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WMOLHGVTKIVYKLAZB3CZCALRLB","short_pith_number":"pith:WMOLHGVT","canonical_record":{"source":{"id":"2002.05527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-12T04:01:57Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"901649b09170957aafba6dadd1de0ea202bd6e56405269be059fd624b82c2297","abstract_canon_sha256":"66021f259cf60ceef683ce42fd18900afd4d40f5798cd0cca3a5aede5b834eaa"},"schema_version":"1.0"},"canonical_sha256":"b31cb39ab3522b852c190ec59101715840b93cddfdeba84f72cd1ad2ed9e0f58","source":{"kind":"arxiv","id":"2002.05527","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05527","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05527v1","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05527","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"WMOLHGVTKIVY","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"WMOLHGVTKIVYKLAZ","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"WMOLHGVT","created_at":"2026-07-05T01:00:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WMOLHGVTKIVYKLAZB3CZCALRLB","target":"record","payload":{"canonical_record":{"source":{"id":"2002.05527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-12T04:01:57Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"901649b09170957aafba6dadd1de0ea202bd6e56405269be059fd624b82c2297","abstract_canon_sha256":"66021f259cf60ceef683ce42fd18900afd4d40f5798cd0cca3a5aede5b834eaa"},"schema_version":"1.0"},"canonical_sha256":"b31cb39ab3522b852c190ec59101715840b93cddfdeba84f72cd1ad2ed9e0f58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:50.061959Z","signature_b64":"IUZOIn2HSHUYXK0aHnT+pUBVghI6/rT5u8g8Cji3kG+GdQLtwAtL7j4DyKnp8Rw/d+VPbEaxWJgtJn7WZbYlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b31cb39ab3522b852c190ec59101715840b93cddfdeba84f72cd1ad2ed9e0f58","last_reissued_at":"2026-07-05T01:00:50.061412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:50.061412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.05527","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:00:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1LWy45Sr0cbRB6gbTC1NF4mB0JbDQ7UmHLDhbpv4s8WBey1zVAzFK9yEfpqGhIEnyOJQYzpTE71X9C/irjAICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T17:20:17.865681Z"},"content_sha256":"245894a3eeabdb2c850a22fa78382b2eac6dd6ec9cfd946d4c52afb6215f8c98","schema_version":"1.0","event_id":"sha256:245894a3eeabdb2c850a22fa78382b2eac6dd6ec9cfd946d4c52afb6215f8c98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WMOLHGVTKIVYKLAZB3CZCALRLB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Separation of Native and Loanwords for Malayalam and Telugu","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Deepak P, Sridhama Prakhya","submitted_at":"2020-02-12T04:01:57Z","abstract_excerpt":"Quite often, words from one language are adopted within a different language without translation; these words appear in transliterated form in text written in the latter language. This phenomenon is particularly widespread within Indian languages where many words are loaned from English. In this paper, we address the task of identifying loanwords automatically and in an unsupervised manner, from large datasets of words from agglutinative Dravidian languages. We target two specific languages from the Dravidian family, viz., Malayalam and Telugu. Based on familiarity with the languages, we outli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05527","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/2002.05527/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:00:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cEImlFQEFkRay9Jv+8v3nDyz0KXuPBDXdPu70BtwOgS2rhGVcWwBkMO1yzSqjyIC7gKrtxU6y0rVQZZlTkswCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T17:20:17.866043Z"},"content_sha256":"b7e6291e0806985f8d118b8a61c8935b1c88509372043962ee47e1a67f35e039","schema_version":"1.0","event_id":"sha256:b7e6291e0806985f8d118b8a61c8935b1c88509372043962ee47e1a67f35e039"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMOLHGVTKIVYKLAZB3CZCALRLB/bundle.json","state_url":"https://pith.science/pith/WMOLHGVTKIVYKLAZB3CZCALRLB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMOLHGVTKIVYKLAZB3CZCALRLB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T17:20:17Z","links":{"resolver":"https://pith.science/pith/WMOLHGVTKIVYKLAZB3CZCALRLB","bundle":"https://pith.science/pith/WMOLHGVTKIVYKLAZB3CZCALRLB/bundle.json","state":"https://pith.science/pith/WMOLHGVTKIVYKLAZB3CZCALRLB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMOLHGVTKIVYKLAZB3CZCALRLB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WMOLHGVTKIVYKLAZB3CZCALRLB","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":"66021f259cf60ceef683ce42fd18900afd4d40f5798cd0cca3a5aede5b834eaa","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-12T04:01:57Z","title_canon_sha256":"901649b09170957aafba6dadd1de0ea202bd6e56405269be059fd624b82c2297"},"schema_version":"1.0","source":{"id":"2002.05527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05527","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05527v1","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05527","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"WMOLHGVTKIVY","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"WMOLHGVTKIVYKLAZ","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"WMOLHGVT","created_at":"2026-07-05T01:00:50Z"}],"graph_snapshots":[{"event_id":"sha256:b7e6291e0806985f8d118b8a61c8935b1c88509372043962ee47e1a67f35e039","target":"graph","created_at":"2026-07-05T01:00:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.05527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quite often, words from one language are adopted within a different language without translation; these words appear in transliterated form in text written in the latter language. This phenomenon is particularly widespread within Indian languages where many words are loaned from English. In this paper, we address the task of identifying loanwords automatically and in an unsupervised manner, from large datasets of words from agglutinative Dravidian languages. We target two specific languages from the Dravidian family, viz., Malayalam and Telugu. Based on familiarity with the languages, we outli","authors_text":"Deepak P, Sridhama Prakhya","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-12T04:01:57Z","title":"Unsupervised Separation of Native and Loanwords for Malayalam and Telugu"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05527","kind":"arxiv","version":1},"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":"sha256:245894a3eeabdb2c850a22fa78382b2eac6dd6ec9cfd946d4c52afb6215f8c98","target":"record","created_at":"2026-07-05T01:00:50Z","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":"66021f259cf60ceef683ce42fd18900afd4d40f5798cd0cca3a5aede5b834eaa","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-12T04:01:57Z","title_canon_sha256":"901649b09170957aafba6dadd1de0ea202bd6e56405269be059fd624b82c2297"},"schema_version":"1.0","source":{"id":"2002.05527","kind":"arxiv","version":1}},"canonical_sha256":"b31cb39ab3522b852c190ec59101715840b93cddfdeba84f72cd1ad2ed9e0f58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b31cb39ab3522b852c190ec59101715840b93cddfdeba84f72cd1ad2ed9e0f58","first_computed_at":"2026-07-05T01:00:50.061412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:50.061412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IUZOIn2HSHUYXK0aHnT+pUBVghI6/rT5u8g8Cji3kG+GdQLtwAtL7j4DyKnp8Rw/d+VPbEaxWJgtJn7WZbYlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:50.061959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.05527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:245894a3eeabdb2c850a22fa78382b2eac6dd6ec9cfd946d4c52afb6215f8c98","sha256:b7e6291e0806985f8d118b8a61c8935b1c88509372043962ee47e1a67f35e039"],"state_sha256":"67eb3b4cb003b5e4fb7692a3dcf93cf6d1af717c9f27aa78d7cfbd5c72f65291"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4dHhSOI1x0Vv8107GNAXsjzx+nlHLfhKD+2UQ0wzg+VjDSwTkzfyj/Mzmk59Kh9h9jodX4Q9YXK+I+CrhtWzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T17:20:17.867991Z","bundle_sha256":"23e9879211d5cd1604d8d48321ba66ac9abfa7b26fafe22bed28cc62036b0801"}}