{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7RQFJ37QR2GXOX7CFPTOVP3FLC","short_pith_number":"pith:7RQFJ37Q","canonical_record":{"source":{"id":"2305.03144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-04T20:53:19Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"41bf207ba1e32044e997b9a61a7953d88f613a3fd5459a5bd4a6fcade1f3ed19","abstract_canon_sha256":"8dfd27b85a9f82249299691a0c82039f90b96e9e4bafac53c49da1a276a933e6"},"schema_version":"1.0"},"canonical_sha256":"fc6054eff08e8d775fe22be6eabf6558b9ee3bafb7d4e5cff391c61cff9b1f71","source":{"kind":"arxiv","id":"2305.03144","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03144","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03144v1","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03144","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"7RQFJ37QR2GX","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"7RQFJ37QR2GXOX7C","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"7RQFJ37Q","created_at":"2026-07-05T06:07:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7RQFJ37QR2GXOX7CFPTOVP3FLC","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-04T20:53:19Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"41bf207ba1e32044e997b9a61a7953d88f613a3fd5459a5bd4a6fcade1f3ed19","abstract_canon_sha256":"8dfd27b85a9f82249299691a0c82039f90b96e9e4bafac53c49da1a276a933e6"},"schema_version":"1.0"},"canonical_sha256":"fc6054eff08e8d775fe22be6eabf6558b9ee3bafb7d4e5cff391c61cff9b1f71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:11.425656Z","signature_b64":"CnzV7ggvauzL8PuRxEhoV1wQuHptDpjzicMnGwudiOrRgI0+eelpbYGziIDsRGU7LrlJ3NfakyskXFobiYmrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc6054eff08e8d775fe22be6eabf6558b9ee3bafb7d4e5cff391c61cff9b1f71","last_reissued_at":"2026-07-05T06:07:11.425305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:11.425305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03144","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":"2026-07-05T06:07:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mmw1MqXHRz+L08gYnL8CksEUGfUT7GBCJElpiyy0GSiSCNSXeLMjYZJ9FtohB1iXZ1zHR9eQbzhV/DcJyoo4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:23:46.521010Z"},"content_sha256":"a8b2dd12da883aeca79934314506535ea1a39858fea8ee979f3a09d48e1be0c9","schema_version":"1.0","event_id":"sha256:a8b2dd12da883aeca79934314506535ea1a39858fea8ee979f3a09d48e1be0c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7RQFJ37QR2GXOX7CFPTOVP3FLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Influence of various text embeddings on clustering performance in NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Rohan Saha","submitted_at":"2023-05-04T20:53:19Z","abstract_excerpt":"With the advent of e-commerce platforms, reviews are crucial for customers to assess the credibility of a product. The star ratings do not always match the review text written by the customer. For example, a three star rating (out of five) may be incongruous with the review text, which may be more suitable for a five star review. A clustering approach can be used to relabel the correct star ratings by grouping the text reviews into individual groups. In this work, we explore the task of choosing different text embeddings to represent these reviews and also explore the impact the embedding choi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03144","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/2305.03144/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":"2026-07-05T06:07:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dnTLv24+Sj0iNHc4+jGO775ZrHQ1Lxdl1JeIW268poYP2j9ErG2+mE3HLqZTJ34zlrHvj0ST5bWcCK+C8GAbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:23:46.521535Z"},"content_sha256":"770a032934217fc81154404099598be9a565c5dc214beb6b17afb2eeda00fd8d","schema_version":"1.0","event_id":"sha256:770a032934217fc81154404099598be9a565c5dc214beb6b17afb2eeda00fd8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7RQFJ37QR2GXOX7CFPTOVP3FLC/bundle.json","state_url":"https://pith.science/pith/7RQFJ37QR2GXOX7CFPTOVP3FLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7RQFJ37QR2GXOX7CFPTOVP3FLC/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":"2026-08-18T06:23:46Z","links":{"resolver":"https://pith.science/pith/7RQFJ37QR2GXOX7CFPTOVP3FLC","bundle":"https://pith.science/pith/7RQFJ37QR2GXOX7CFPTOVP3FLC/bundle.json","state":"https://pith.science/pith/7RQFJ37QR2GXOX7CFPTOVP3FLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7RQFJ37QR2GXOX7CFPTOVP3FLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7RQFJ37QR2GXOX7CFPTOVP3FLC","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":"8dfd27b85a9f82249299691a0c82039f90b96e9e4bafac53c49da1a276a933e6","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-04T20:53:19Z","title_canon_sha256":"41bf207ba1e32044e997b9a61a7953d88f613a3fd5459a5bd4a6fcade1f3ed19"},"schema_version":"1.0","source":{"id":"2305.03144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03144","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03144v1","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03144","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"7RQFJ37QR2GX","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"7RQFJ37QR2GXOX7C","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"7RQFJ37Q","created_at":"2026-07-05T06:07:11Z"}],"graph_snapshots":[{"event_id":"sha256:770a032934217fc81154404099598be9a565c5dc214beb6b17afb2eeda00fd8d","target":"graph","created_at":"2026-07-05T06:07:11Z","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/2305.03144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advent of e-commerce platforms, reviews are crucial for customers to assess the credibility of a product. The star ratings do not always match the review text written by the customer. For example, a three star rating (out of five) may be incongruous with the review text, which may be more suitable for a five star review. A clustering approach can be used to relabel the correct star ratings by grouping the text reviews into individual groups. In this work, we explore the task of choosing different text embeddings to represent these reviews and also explore the impact the embedding choi","authors_text":"Rohan Saha","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-04T20:53:19Z","title":"Influence of various text embeddings on clustering performance in NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03144","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:a8b2dd12da883aeca79934314506535ea1a39858fea8ee979f3a09d48e1be0c9","target":"record","created_at":"2026-07-05T06:07:11Z","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":"8dfd27b85a9f82249299691a0c82039f90b96e9e4bafac53c49da1a276a933e6","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-04T20:53:19Z","title_canon_sha256":"41bf207ba1e32044e997b9a61a7953d88f613a3fd5459a5bd4a6fcade1f3ed19"},"schema_version":"1.0","source":{"id":"2305.03144","kind":"arxiv","version":1}},"canonical_sha256":"fc6054eff08e8d775fe22be6eabf6558b9ee3bafb7d4e5cff391c61cff9b1f71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc6054eff08e8d775fe22be6eabf6558b9ee3bafb7d4e5cff391c61cff9b1f71","first_computed_at":"2026-07-05T06:07:11.425305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:11.425305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CnzV7ggvauzL8PuRxEhoV1wQuHptDpjzicMnGwudiOrRgI0+eelpbYGziIDsRGU7LrlJ3NfakyskXFobiYmrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:11.425656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8b2dd12da883aeca79934314506535ea1a39858fea8ee979f3a09d48e1be0c9","sha256:770a032934217fc81154404099598be9a565c5dc214beb6b17afb2eeda00fd8d"],"state_sha256":"05ec4699958409185a2eb3ac8fb9b0669574d958ba981cb8975306a3a1695498"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W1JRrLHieLhLGhUnu5Fo6ZuzvKbzMI8GiByo8LnrsyVcKZgoFxCdjC7pDKUoyt/8O76xXQlxBgjlbzBGXpwkBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:23:46.527780Z","bundle_sha256":"4f8abe9004af2c21a0e2b06e17c858aaeb8fd9c0bb06ef27ac01bdff02d73ee6"}}