{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:D5NXII6NY7DCPTDACWMDW6LLL7","short_pith_number":"pith:D5NXII6N","canonical_record":{"source":{"id":"2210.11753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T06:15:40Z","cross_cats_sorted":[],"title_canon_sha256":"0887bd2d8f75c32cd2abe5a8aff9cd7a59142c9393f5ae9e83dfd8c3b2154bb7","abstract_canon_sha256":"300da02bb52b303c3688996b9fb20f35fe36e985620116ad95b5b8678047f40b"},"schema_version":"1.0"},"canonical_sha256":"1f5b7423cdc7c627cc6015983b796b5ffb12cd6bb4646fa0945d36b3acffaccc","source":{"kind":"arxiv","id":"2210.11753","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11753","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11753v1","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11753","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"D5NXII6NY7DC","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"pith_short_16","alias_value":"D5NXII6NY7DCPTDA","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"pith_short_8","alias_value":"D5NXII6N","created_at":"2026-07-05T05:08:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:D5NXII6NY7DCPTDACWMDW6LLL7","target":"record","payload":{"canonical_record":{"source":{"id":"2210.11753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T06:15:40Z","cross_cats_sorted":[],"title_canon_sha256":"0887bd2d8f75c32cd2abe5a8aff9cd7a59142c9393f5ae9e83dfd8c3b2154bb7","abstract_canon_sha256":"300da02bb52b303c3688996b9fb20f35fe36e985620116ad95b5b8678047f40b"},"schema_version":"1.0"},"canonical_sha256":"1f5b7423cdc7c627cc6015983b796b5ffb12cd6bb4646fa0945d36b3acffaccc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:57.231205Z","signature_b64":"+l6juCYKlVjr3zOvD1Yocu0nqL+2FojUfTInx1lTxcfNka4wAV7gsmFS7Bp5L8up3kDlwuS3Tzek7iRM7lsCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f5b7423cdc7c627cc6015983b796b5ffb12cd6bb4646fa0945d36b3acffaccc","last_reissued_at":"2026-07-05T05:08:57.230816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:57.230816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.11753","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":"2026-07-05T05:08:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yU7aMYFOT1Zu6GXN0pyRhsjddE1lJeSM4gT5eTewAcqAur7EaoiH+gVdyA7XVjkKoGqi714DV2r9KclOQa02Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T17:46:23.613993Z"},"content_sha256":"5568bd30c07b2da10700a6db0b7a9acf9d4328488973b2037c94ffb74f781ec6","schema_version":"1.0","event_id":"sha256:5568bd30c07b2da10700a6db0b7a9acf9d4328488973b2037c94ffb74f781ec6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:D5NXII6NY7DCPTDACWMDW6LLL7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jivnesh Sandhan, Laxmidhar Behera, Narein Rao, Pawan Goyal, Rathin Singha, Suvendu Samanta","submitted_at":"2022-10-21T06:15:40Z","abstract_excerpt":"Sanskrit Word Segmentation (SWS) is essential in making digitized texts available and in deploying downstream tasks. It is, however, non-trivial because of the sandhi phenomenon that modifies the characters at the word boundaries, and needs special treatment. Existing lexicon driven approaches for SWS make use of Sanskrit Heritage Reader, a lexicon-driven shallow parser, to generate the complete candidate solution space, over which various methods are applied to produce the most valid solution. However, these approaches fail while encountering out-of-vocabulary tokens. On the other hand, purel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11753","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/2210.11753/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":"2026-07-05T05:08:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jp7Z3HmGwM9gCAnXftQfuky7omqxhA35Oc+nmhbI3XfVukFnGXEjnwSDHRjg5duPPwrFcE8xdY/SdGb6SQqQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T17:46:23.614377Z"},"content_sha256":"f2e3ee155f42a6c6175c112d8a74a8376622194446ab94061188bd140d51b150","schema_version":"1.0","event_id":"sha256:f2e3ee155f42a6c6175c112d8a74a8376622194446ab94061188bd140d51b150"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D5NXII6NY7DCPTDACWMDW6LLL7/bundle.json","state_url":"https://pith.science/pith/D5NXII6NY7DCPTDACWMDW6LLL7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D5NXII6NY7DCPTDACWMDW6LLL7/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":"2026-07-20T17:46:23Z","links":{"resolver":"https://pith.science/pith/D5NXII6NY7DCPTDACWMDW6LLL7","bundle":"https://pith.science/pith/D5NXII6NY7DCPTDACWMDW6LLL7/bundle.json","state":"https://pith.science/pith/D5NXII6NY7DCPTDACWMDW6LLL7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D5NXII6NY7DCPTDACWMDW6LLL7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:D5NXII6NY7DCPTDACWMDW6LLL7","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":"300da02bb52b303c3688996b9fb20f35fe36e985620116ad95b5b8678047f40b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T06:15:40Z","title_canon_sha256":"0887bd2d8f75c32cd2abe5a8aff9cd7a59142c9393f5ae9e83dfd8c3b2154bb7"},"schema_version":"1.0","source":{"id":"2210.11753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11753","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11753v1","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11753","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"D5NXII6NY7DC","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"pith_short_16","alias_value":"D5NXII6NY7DCPTDA","created_at":"2026-07-05T05:08:57Z"},{"alias_kind":"pith_short_8","alias_value":"D5NXII6N","created_at":"2026-07-05T05:08:57Z"}],"graph_snapshots":[{"event_id":"sha256:f2e3ee155f42a6c6175c112d8a74a8376622194446ab94061188bd140d51b150","target":"graph","created_at":"2026-07-05T05:08:57Z","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/2210.11753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sanskrit Word Segmentation (SWS) is essential in making digitized texts available and in deploying downstream tasks. It is, however, non-trivial because of the sandhi phenomenon that modifies the characters at the word boundaries, and needs special treatment. Existing lexicon driven approaches for SWS make use of Sanskrit Heritage Reader, a lexicon-driven shallow parser, to generate the complete candidate solution space, over which various methods are applied to produce the most valid solution. However, these approaches fail while encountering out-of-vocabulary tokens. On the other hand, purel","authors_text":"Jivnesh Sandhan, Laxmidhar Behera, Narein Rao, Pawan Goyal, Rathin Singha, Suvendu Samanta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T06:15:40Z","title":"TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11753","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":"sha256:5568bd30c07b2da10700a6db0b7a9acf9d4328488973b2037c94ffb74f781ec6","target":"record","created_at":"2026-07-05T05:08:57Z","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":"300da02bb52b303c3688996b9fb20f35fe36e985620116ad95b5b8678047f40b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T06:15:40Z","title_canon_sha256":"0887bd2d8f75c32cd2abe5a8aff9cd7a59142c9393f5ae9e83dfd8c3b2154bb7"},"schema_version":"1.0","source":{"id":"2210.11753","kind":"arxiv","version":1}},"canonical_sha256":"1f5b7423cdc7c627cc6015983b796b5ffb12cd6bb4646fa0945d36b3acffaccc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f5b7423cdc7c627cc6015983b796b5ffb12cd6bb4646fa0945d36b3acffaccc","first_computed_at":"2026-07-05T05:08:57.230816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:57.230816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+l6juCYKlVjr3zOvD1Yocu0nqL+2FojUfTInx1lTxcfNka4wAV7gsmFS7Bp5L8up3kDlwuS3Tzek7iRM7lsCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:57.231205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5568bd30c07b2da10700a6db0b7a9acf9d4328488973b2037c94ffb74f781ec6","sha256:f2e3ee155f42a6c6175c112d8a74a8376622194446ab94061188bd140d51b150"],"state_sha256":"3a93f9cbb122f1fde01fcac2ef20f88f4acba6c8f93addb75fa3a11c4a496efd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqT+TwAY/FXGAj/XoN1U08dA8Z7VAuqkUJFYm+wI+hq8OM/juGGaX/3bUGRTsdjhOTAUy1UdDU08y1HQcPEsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T17:46:23.616909Z","bundle_sha256":"b975de22014e7a480bdded7fbd01d3321559a1927e35465def76bc42b5292bd5"}}