{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TUQ7AKFUES3OGPV6IZPEQZK5WL","short_pith_number":"pith:TUQ7AKFU","canonical_record":{"source":{"id":"2506.18602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T13:03:59Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"6e1ec705a6c4c640b54bfb38f7e6708c1b1b616f75e1dc2b45d8b184216c7ea3","abstract_canon_sha256":"6efcd3e84b1c135c0fa126da41d658744a62f0ac14cf193c8d0e1eeca15fce18"},"schema_version":"1.0"},"canonical_sha256":"9d21f028b424b6e33ebe465e48655db2c3cce19f2f369aa0bea2efa14f141761","source":{"kind":"arxiv","id":"2506.18602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18602","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18602v1","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18602","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"pith_short_12","alias_value":"TUQ7AKFUES3O","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"pith_short_16","alias_value":"TUQ7AKFUES3OGPV6","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"pith_short_8","alias_value":"TUQ7AKFU","created_at":"2026-07-05T11:25:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TUQ7AKFUES3OGPV6IZPEQZK5WL","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T13:03:59Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"6e1ec705a6c4c640b54bfb38f7e6708c1b1b616f75e1dc2b45d8b184216c7ea3","abstract_canon_sha256":"6efcd3e84b1c135c0fa126da41d658744a62f0ac14cf193c8d0e1eeca15fce18"},"schema_version":"1.0"},"canonical_sha256":"9d21f028b424b6e33ebe465e48655db2c3cce19f2f369aa0bea2efa14f141761","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:52.861410Z","signature_b64":"0QgzK9Fn7yhl3LMCyY1PeTwIPGKAUn9gFGode4hYhtEcgc0dmAYjQ4/14p/calEagReKlM5+PZqViRwdCh+QAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d21f028b424b6e33ebe465e48655db2c3cce19f2f369aa0bea2efa14f141761","last_reissued_at":"2026-07-05T11:25:52.860931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:52.860931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18602","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":"2026-07-05T11:25:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/8IitirIJ2xagZXx3p20ZjbuiW3DgLbXsqjW1YHYDtzlvO7/daYwyCZtJ6MguFsDvhMyfAmv7CRmPUzhRUveCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:05:26.633985Z"},"content_sha256":"df53c9252f70da39c17bb751ba94c728ad372f14765483dbbdd992ae409204e7","schema_version":"1.0","event_id":"sha256:df53c9252f70da39c17bb751ba94c728ad372f14765483dbbdd992ae409204e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TUQ7AKFUES3OGPV6IZPEQZK5WL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic similarity estimation for domain specific data using BERT and other techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.CL","authors_text":"R. Prashanth","submitted_at":"2025-06-23T13:03:59Z","abstract_excerpt":"Estimation of semantic similarity is an important research problem both in natural language processing and the natural language understanding, and that has tremendous application on various downstream tasks such as question answering, semantic search, information retrieval, document clustering, word-sense disambiguation and machine translation. In this work, we carry out the estimation of semantic similarity using different state-of-the-art techniques including the USE (Universal Sentence Encoder), InferSent and the most recent BERT, or Bidirectional Encoder Representations from Transformers, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18602","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/2506.18602/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":"2026-07-05T11:25:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceavQM3jtwmYGDtrlSfvlFe6bKuX4z4JxFyLbWkExUxnB8BMSQrOUm9oaPPzvHopF/YdwaJVr8ZzVR8bWrUnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:05:26.634913Z"},"content_sha256":"c1a7965c7899852eae0a40ec47414a03f38dd34dea568ca52b328ba680775e65","schema_version":"1.0","event_id":"sha256:c1a7965c7899852eae0a40ec47414a03f38dd34dea568ca52b328ba680775e65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUQ7AKFUES3OGPV6IZPEQZK5WL/bundle.json","state_url":"https://pith.science/pith/TUQ7AKFUES3OGPV6IZPEQZK5WL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUQ7AKFUES3OGPV6IZPEQZK5WL/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":"2026-08-04T16:05:26Z","links":{"resolver":"https://pith.science/pith/TUQ7AKFUES3OGPV6IZPEQZK5WL","bundle":"https://pith.science/pith/TUQ7AKFUES3OGPV6IZPEQZK5WL/bundle.json","state":"https://pith.science/pith/TUQ7AKFUES3OGPV6IZPEQZK5WL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUQ7AKFUES3OGPV6IZPEQZK5WL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TUQ7AKFUES3OGPV6IZPEQZK5WL","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":"6efcd3e84b1c135c0fa126da41d658744a62f0ac14cf193c8d0e1eeca15fce18","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T13:03:59Z","title_canon_sha256":"6e1ec705a6c4c640b54bfb38f7e6708c1b1b616f75e1dc2b45d8b184216c7ea3"},"schema_version":"1.0","source":{"id":"2506.18602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18602","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18602v1","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18602","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"pith_short_12","alias_value":"TUQ7AKFUES3O","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"pith_short_16","alias_value":"TUQ7AKFUES3OGPV6","created_at":"2026-07-05T11:25:52Z"},{"alias_kind":"pith_short_8","alias_value":"TUQ7AKFU","created_at":"2026-07-05T11:25:52Z"}],"graph_snapshots":[{"event_id":"sha256:c1a7965c7899852eae0a40ec47414a03f38dd34dea568ca52b328ba680775e65","target":"graph","created_at":"2026-07-05T11:25:52Z","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/2506.18602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Estimation of semantic similarity is an important research problem both in natural language processing and the natural language understanding, and that has tremendous application on various downstream tasks such as question answering, semantic search, information retrieval, document clustering, word-sense disambiguation and machine translation. In this work, we carry out the estimation of semantic similarity using different state-of-the-art techniques including the USE (Universal Sentence Encoder), InferSent and the most recent BERT, or Bidirectional Encoder Representations from Transformers, ","authors_text":"R. Prashanth","cross_cats":["stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T13:03:59Z","title":"Semantic similarity estimation for domain specific data using BERT and other techniques"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18602","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:df53c9252f70da39c17bb751ba94c728ad372f14765483dbbdd992ae409204e7","target":"record","created_at":"2026-07-05T11:25:52Z","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":"6efcd3e84b1c135c0fa126da41d658744a62f0ac14cf193c8d0e1eeca15fce18","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T13:03:59Z","title_canon_sha256":"6e1ec705a6c4c640b54bfb38f7e6708c1b1b616f75e1dc2b45d8b184216c7ea3"},"schema_version":"1.0","source":{"id":"2506.18602","kind":"arxiv","version":1}},"canonical_sha256":"9d21f028b424b6e33ebe465e48655db2c3cce19f2f369aa0bea2efa14f141761","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d21f028b424b6e33ebe465e48655db2c3cce19f2f369aa0bea2efa14f141761","first_computed_at":"2026-07-05T11:25:52.860931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:52.860931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0QgzK9Fn7yhl3LMCyY1PeTwIPGKAUn9gFGode4hYhtEcgc0dmAYjQ4/14p/calEagReKlM5+PZqViRwdCh+QAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:52.861410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df53c9252f70da39c17bb751ba94c728ad372f14765483dbbdd992ae409204e7","sha256:c1a7965c7899852eae0a40ec47414a03f38dd34dea568ca52b328ba680775e65"],"state_sha256":"8b9c2615a0470ac4414c92aa4d6554c6f80877a87e4577c307391a14ba6072a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"48AVNfyJruUTjcfwnZMkemnngmC5IsPtPa/24OIwc9/gnEtBJhohHLrHb5aL2lwo2eJMErCLRPXRN4EeSEZlBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:05:26.641753Z","bundle_sha256":"304bece169f7ada7f4b47a0c4cc1aea0b423533a2c21cfe53c73b1d27edf4eff"}}