{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WOYQWJG6NUJLMK4ZYF7KVSDYUK","short_pith_number":"pith:WOYQWJG6","canonical_record":{"source":{"id":"1802.06185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-17T04:05:36Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c6597f63cff9d95cd69ab8035a2f703a3910c0d70fa2e01d4c145cbf43e7053f","abstract_canon_sha256":"ac68ea04c3f7dd47b56ce3035c443f75d2942bbafad0ff84f545472157471d7d"},"schema_version":"1.0"},"canonical_sha256":"b3b10b24de6d12b62b99c17eaac878a2803a32bd4e094ebc0acf5707cb5ce04f","source":{"kind":"arxiv","id":"1802.06185","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06185","created_at":"2026-05-18T00:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06185v1","created_at":"2026-05-18T00:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06185","created_at":"2026-05-18T00:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"WOYQWJG6NUJL","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WOYQWJG6NUJLMK4Z","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WOYQWJG6","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WOYQWJG6NUJLMK4ZYF7KVSDYUK","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-17T04:05:36Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c6597f63cff9d95cd69ab8035a2f703a3910c0d70fa2e01d4c145cbf43e7053f","abstract_canon_sha256":"ac68ea04c3f7dd47b56ce3035c443f75d2942bbafad0ff84f545472157471d7d"},"schema_version":"1.0"},"canonical_sha256":"b3b10b24de6d12b62b99c17eaac878a2803a32bd4e094ebc0acf5707cb5ce04f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:04.174680Z","signature_b64":"Ko3GyfSCq/ePw7kPviElMewwGRaqUPas9loPNiTse0XycmBauYunPJihry079NurAspitlYFkNymmPOBBwZsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3b10b24de6d12b62b99c17eaac878a2803a32bd4e094ebc0acf5707cb5ce04f","last_reissued_at":"2026-05-18T00:23:04.173842Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:04.173842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06185","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":"2026-05-18T00:23:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Da8LKF/Kkb0DWo7Zf0qcedP19FxSu3Xp6ip1r3QEHCze7+47nH/6Ha7ijkiM4PxTTgl46J8TbJgODdImb5LiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T17:18:50.425380Z"},"content_sha256":"b067e1da4b8f0346e289fa3a005521f6253953d127d7cbbb739ca337cab039b6","schema_version":"1.0","event_id":"sha256:b067e1da4b8f0346e289fa3a005521f6253953d127d7cbbb739ca337cab039b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WOYQWJG6NUJLMK4ZYF7KVSDYUK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building a Word Segmenter for Sanskrit Overnight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Amrith Krishna, Pawan Goyal, Prateek Gupta, Vikas Reddy, Vineeth M R, Vishnu Dutt Sharma","submitted_at":"2018-02-17T04:05:36Z","abstract_excerpt":"There is an abundance of digitised texts available in Sanskrit. However, the word segmentation task in such texts are challenging due to the issue of 'Sandhi'. In Sandhi, words in a sentence often fuse together to form a single chunk of text, where the word delimiter vanishes and sounds at the word boundaries undergo transformations, which is also reflected in the written text. Here, we propose an approach that uses a deep sequence to sequence (seq2seq) model that takes only the sandhied string as the input and predicts the unsandhied string. The state of the art models are linguistically invo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06185","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":"2026-05-18T00:23:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qgL/1a2wXbeAcp4ZFxgUeLiaREN2qkKXUbEf6U/ic0THRf0JS2H08BHD5pqQZV7zVavPTgg7zFMgNrJhz/vHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T17:18:50.426087Z"},"content_sha256":"3fc52550633d3e3ae8f2a000fdd69075261d6aed671df71d33889a42723f56a9","schema_version":"1.0","event_id":"sha256:3fc52550633d3e3ae8f2a000fdd69075261d6aed671df71d33889a42723f56a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOYQWJG6NUJLMK4ZYF7KVSDYUK/bundle.json","state_url":"https://pith.science/pith/WOYQWJG6NUJLMK4ZYF7KVSDYUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOYQWJG6NUJLMK4ZYF7KVSDYUK/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":"2026-05-29T17:18:50Z","links":{"resolver":"https://pith.science/pith/WOYQWJG6NUJLMK4ZYF7KVSDYUK","bundle":"https://pith.science/pith/WOYQWJG6NUJLMK4ZYF7KVSDYUK/bundle.json","state":"https://pith.science/pith/WOYQWJG6NUJLMK4ZYF7KVSDYUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOYQWJG6NUJLMK4ZYF7KVSDYUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WOYQWJG6NUJLMK4ZYF7KVSDYUK","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":"ac68ea04c3f7dd47b56ce3035c443f75d2942bbafad0ff84f545472157471d7d","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-17T04:05:36Z","title_canon_sha256":"c6597f63cff9d95cd69ab8035a2f703a3910c0d70fa2e01d4c145cbf43e7053f"},"schema_version":"1.0","source":{"id":"1802.06185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06185","created_at":"2026-05-18T00:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06185v1","created_at":"2026-05-18T00:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06185","created_at":"2026-05-18T00:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"WOYQWJG6NUJL","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WOYQWJG6NUJLMK4Z","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WOYQWJG6","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:3fc52550633d3e3ae8f2a000fdd69075261d6aed671df71d33889a42723f56a9","target":"graph","created_at":"2026-05-18T00:23:04Z","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":"There is an abundance of digitised texts available in Sanskrit. However, the word segmentation task in such texts are challenging due to the issue of 'Sandhi'. In Sandhi, words in a sentence often fuse together to form a single chunk of text, where the word delimiter vanishes and sounds at the word boundaries undergo transformations, which is also reflected in the written text. Here, we propose an approach that uses a deep sequence to sequence (seq2seq) model that takes only the sandhied string as the input and predicts the unsandhied string. The state of the art models are linguistically invo","authors_text":"Amrith Krishna, Pawan Goyal, Prateek Gupta, Vikas Reddy, Vineeth M R, Vishnu Dutt Sharma","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-17T04:05:36Z","title":"Building a Word Segmenter for Sanskrit Overnight"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06185","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:b067e1da4b8f0346e289fa3a005521f6253953d127d7cbbb739ca337cab039b6","target":"record","created_at":"2026-05-18T00:23:04Z","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":"ac68ea04c3f7dd47b56ce3035c443f75d2942bbafad0ff84f545472157471d7d","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-17T04:05:36Z","title_canon_sha256":"c6597f63cff9d95cd69ab8035a2f703a3910c0d70fa2e01d4c145cbf43e7053f"},"schema_version":"1.0","source":{"id":"1802.06185","kind":"arxiv","version":1}},"canonical_sha256":"b3b10b24de6d12b62b99c17eaac878a2803a32bd4e094ebc0acf5707cb5ce04f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3b10b24de6d12b62b99c17eaac878a2803a32bd4e094ebc0acf5707cb5ce04f","first_computed_at":"2026-05-18T00:23:04.173842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:04.173842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ko3GyfSCq/ePw7kPviElMewwGRaqUPas9loPNiTse0XycmBauYunPJihry079NurAspitlYFkNymmPOBBwZsBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:04.174680Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b067e1da4b8f0346e289fa3a005521f6253953d127d7cbbb739ca337cab039b6","sha256:3fc52550633d3e3ae8f2a000fdd69075261d6aed671df71d33889a42723f56a9"],"state_sha256":"7c6059408ef730bda30a63af8b1eccc3f8f73c6d926a7774516c746e8720098a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"itd7hRiNZQ6c63ReRrrZ0PrQ7Ie1fDy0oR6CFyGBtLeTiSKnddnf/EsES9bmQ09rCbjqWZbPtMwlWpLvb0BfAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T17:18:50.429947Z","bundle_sha256":"a0a20ab5caf6a118a32c72677b57d47590f811ebba76598ca6d20f702719c9f0"}}