{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ZYC4V6TI3VNUAI7MQSEIMOGBS2","short_pith_number":"pith:ZYC4V6TI","canonical_record":{"source":{"id":"1701.00066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-31T07:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"ad8027587a5f476a3047505045105bf4f61d6d6791bbefb758dbfddb75e05230","abstract_canon_sha256":"d115449c54218574a748e1b988e5015aab7dc3a77c9cc1fcdf60e7b08bda21a5"},"schema_version":"1.0"},"canonical_sha256":"ce05cafa68dd5b4023ec84888638c1969ae9588d4ec68861c5d8757c441dcca7","source":{"kind":"arxiv","id":"1701.00066","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.00066","created_at":"2026-05-18T00:53:39Z"},{"alias_kind":"arxiv_version","alias_value":"1701.00066v1","created_at":"2026-05-18T00:53:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00066","created_at":"2026-05-18T00:53:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZYC4V6TI3VNU","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZYC4V6TI3VNUAI7M","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZYC4V6TI","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ZYC4V6TI3VNUAI7MQSEIMOGBS2","target":"record","payload":{"canonical_record":{"source":{"id":"1701.00066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-31T07:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"ad8027587a5f476a3047505045105bf4f61d6d6791bbefb758dbfddb75e05230","abstract_canon_sha256":"d115449c54218574a748e1b988e5015aab7dc3a77c9cc1fcdf60e7b08bda21a5"},"schema_version":"1.0"},"canonical_sha256":"ce05cafa68dd5b4023ec84888638c1969ae9588d4ec68861c5d8757c441dcca7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:39.513819Z","signature_b64":"jZJlIESvupLdoQ8fMKERn+cmCFCQy+5zpACm3U5tzFcnqH8FRly7ZfC2kZMcS7VpVEhR7wH9MgxF1qpNka9jAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce05cafa68dd5b4023ec84888638c1969ae9588d4ec68861c5d8757c441dcca7","last_reissued_at":"2026-05-18T00:53:39.513376Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:39.513376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.00066","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":"2026-05-18T00:53:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wx46EU+jwbJL42STk7QOQKCAnyrXndfiSzCPOS1IZ6Iuu29iQo0Tj6WrW8BE3HYogitQB+2Vkb7FSvLOMU5kDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T00:11:44.574233Z"},"content_sha256":"3b8c6333360d51b214213beb2fcebafea6daf9b97d9c76f4187d322f5f0149ce","schema_version":"1.0","event_id":"sha256:3b8c6333360d51b214213beb2fcebafea6daf9b97d9c76f4187d322f5f0149ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ZYC4V6TI3VNUAI7MQSEIMOGBS2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A POS Tagger for Code Mixed Indian Social Media Text - ICON-2016 NLP Tools Contest Entry from Surukam","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Raveena R Kumar, Sree Harsha Ramesh","submitted_at":"2016-12-31T07:09:52Z","abstract_excerpt":"Building Part-of-Speech (POS) taggers for code-mixed Indian languages is a particularly challenging problem in computational linguistics due to a dearth of accurately annotated training corpora. ICON, as part of its NLP tools contest has organized this challenge as a shared task for the second consecutive year to improve the state-of-the-art. This paper describes the POS tagger built at Surukam to predict the coarse-grained and fine-grained POS tags for three language pairs - Bengali-English, Telugu-English and Hindi-English, with the text spanning three popular social media platforms - Facebo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00066","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":""},"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":"2026-05-18T00:53:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OQTDHj1FfcNDGjWYVS3SGYqMsgYyRBYsbR4oRo6K2nwQscmqwqEmZC/TjiTd6eQ9YYXpr/YTB3mT0/xJHRyaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T00:11:44.574598Z"},"content_sha256":"8a6923c20ec7479c1e1825e9a2d99e4d2cf3712bd6376472c6a3ba4cc38c841b","schema_version":"1.0","event_id":"sha256:8a6923c20ec7479c1e1825e9a2d99e4d2cf3712bd6376472c6a3ba4cc38c841b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYC4V6TI3VNUAI7MQSEIMOGBS2/bundle.json","state_url":"https://pith.science/pith/ZYC4V6TI3VNUAI7MQSEIMOGBS2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYC4V6TI3VNUAI7MQSEIMOGBS2/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":"2026-06-20T00:11:44Z","links":{"resolver":"https://pith.science/pith/ZYC4V6TI3VNUAI7MQSEIMOGBS2","bundle":"https://pith.science/pith/ZYC4V6TI3VNUAI7MQSEIMOGBS2/bundle.json","state":"https://pith.science/pith/ZYC4V6TI3VNUAI7MQSEIMOGBS2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYC4V6TI3VNUAI7MQSEIMOGBS2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ZYC4V6TI3VNUAI7MQSEIMOGBS2","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":"d115449c54218574a748e1b988e5015aab7dc3a77c9cc1fcdf60e7b08bda21a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-31T07:09:52Z","title_canon_sha256":"ad8027587a5f476a3047505045105bf4f61d6d6791bbefb758dbfddb75e05230"},"schema_version":"1.0","source":{"id":"1701.00066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.00066","created_at":"2026-05-18T00:53:39Z"},{"alias_kind":"arxiv_version","alias_value":"1701.00066v1","created_at":"2026-05-18T00:53:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00066","created_at":"2026-05-18T00:53:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZYC4V6TI3VNU","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZYC4V6TI3VNUAI7M","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZYC4V6TI","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:8a6923c20ec7479c1e1825e9a2d99e4d2cf3712bd6376472c6a3ba4cc38c841b","target":"graph","created_at":"2026-05-18T00:53:39Z","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"},"paper":{"abstract_excerpt":"Building Part-of-Speech (POS) taggers for code-mixed Indian languages is a particularly challenging problem in computational linguistics due to a dearth of accurately annotated training corpora. ICON, as part of its NLP tools contest has organized this challenge as a shared task for the second consecutive year to improve the state-of-the-art. This paper describes the POS tagger built at Surukam to predict the coarse-grained and fine-grained POS tags for three language pairs - Bengali-English, Telugu-English and Hindi-English, with the text spanning three popular social media platforms - Facebo","authors_text":"Raveena R Kumar, Sree Harsha Ramesh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-31T07:09:52Z","title":"A POS Tagger for Code Mixed Indian Social Media Text - ICON-2016 NLP Tools Contest Entry from Surukam"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00066","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":"sha256:3b8c6333360d51b214213beb2fcebafea6daf9b97d9c76f4187d322f5f0149ce","target":"record","created_at":"2026-05-18T00:53:39Z","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":"d115449c54218574a748e1b988e5015aab7dc3a77c9cc1fcdf60e7b08bda21a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-31T07:09:52Z","title_canon_sha256":"ad8027587a5f476a3047505045105bf4f61d6d6791bbefb758dbfddb75e05230"},"schema_version":"1.0","source":{"id":"1701.00066","kind":"arxiv","version":1}},"canonical_sha256":"ce05cafa68dd5b4023ec84888638c1969ae9588d4ec68861c5d8757c441dcca7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce05cafa68dd5b4023ec84888638c1969ae9588d4ec68861c5d8757c441dcca7","first_computed_at":"2026-05-18T00:53:39.513376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:39.513376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jZJlIESvupLdoQ8fMKERn+cmCFCQy+5zpACm3U5tzFcnqH8FRly7ZfC2kZMcS7VpVEhR7wH9MgxF1qpNka9jAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:39.513819Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.00066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b8c6333360d51b214213beb2fcebafea6daf9b97d9c76f4187d322f5f0149ce","sha256:8a6923c20ec7479c1e1825e9a2d99e4d2cf3712bd6376472c6a3ba4cc38c841b"],"state_sha256":"d9ce00050c8453646bbf2e5ccd9a39726ae273e03c6567ad13b959f672c3685a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LdfoVbF6rRZyBysIa5HmZOaGw9OAzfHzBF/0wqymX6Q9OocZ/6Mg8XzxY1Y8773IBB+tcY7Bk6rb7zeP5XOWAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T00:11:44.576460Z","bundle_sha256":"6c23a68515214c061bc43b76d1e40d26b1e7fe6b78a3bf123ed92c3386d8342c"}}