{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:THG3XM5WKAKFQSQOFTVMO6UQSY","short_pith_number":"pith:THG3XM5W","canonical_record":{"source":{"id":"2505.05269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T14:15:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"25c6778d84b4831e0649799a7f6fb423129db5332b701109ad8eedcee1c311d1","abstract_canon_sha256":"60ecdc4acab00f190090e36d68ad93ebc2adf1fbe86ebbfb2473f716ac2cdfc2"},"schema_version":"1.0"},"canonical_sha256":"99cdbbb3b65014584a0e2ceac77a909611901acfe67fa4903b0962d8a7851143","source":{"kind":"arxiv","id":"2505.05269","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05269","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05269v1","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05269","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"THG3XM5WKAKF","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"pith_short_16","alias_value":"THG3XM5WKAKFQSQO","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"pith_short_8","alias_value":"THG3XM5W","created_at":"2026-07-05T11:00:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:THG3XM5WKAKFQSQOFTVMO6UQSY","target":"record","payload":{"canonical_record":{"source":{"id":"2505.05269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T14:15:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"25c6778d84b4831e0649799a7f6fb423129db5332b701109ad8eedcee1c311d1","abstract_canon_sha256":"60ecdc4acab00f190090e36d68ad93ebc2adf1fbe86ebbfb2473f716ac2cdfc2"},"schema_version":"1.0"},"canonical_sha256":"99cdbbb3b65014584a0e2ceac77a909611901acfe67fa4903b0962d8a7851143","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:21.854396Z","signature_b64":"czCAaM2cOCkpqCcwz1J/kfqtx061axBc6th37WNZhDGE5olZsIdJe+ilz11VMoyfXmOPAyMdVTggq+qtTp7tBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99cdbbb3b65014584a0e2ceac77a909611901acfe67fa4903b0962d8a7851143","last_reissued_at":"2026-07-05T11:00:21.853863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:21.853863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.05269","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":"2026-07-05T11:00:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MKHB8akhz8FxKYd0agC+7Wwz2FY2HPOkr/U2FeMR8XWmz18DfREN7Y3v9f43iZwmya6NAnuuMpGN54axNxAcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:17:42.310478Z"},"content_sha256":"8c088f886ac2da0839b23e061845d00ff8287d09573f54ec77eba3720e495a25","schema_version":"1.0","event_id":"sha256:8c088f886ac2da0839b23e061845d00ff8287d09573f54ec77eba3720e495a25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:THG3XM5WKAKFQSQOFTVMO6UQSY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Two-Sample Test of Text Generation Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chen Qian, Feng Guo, Jingbin Xu, Meimei Liu","submitted_at":"2025-05-08T14:15:53Z","abstract_excerpt":"The surge in digitized text data requires reliable inferential methods on observed textual patterns. This article proposes a novel two-sample text test for comparing similarity between two groups of documents. The hypothesis is whether the probabilistic mapping generating the textual data is identical across two groups of documents. The proposed test aims to assess text similarity by comparing the entropy of the documents. Entropy is estimated using neural network-based language models. The test statistic is derived from an estimation-and-inference framework, where the entropy is first approxi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05269","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/2505.05269/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":"2026-07-05T11:00:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"37NaAMiUY4j1Y0TmUF2NMf1U0qUvYvhLd+ZExyCLbNnXGmSu1bqqYuoL6S1C8zUxVxcMKRyIgTr1QoHbhrjTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:17:42.311054Z"},"content_sha256":"478e272b5ddfdf1043022b734c7412cefdd6e64de5bfa4517ae580b0f13a3709","schema_version":"1.0","event_id":"sha256:478e272b5ddfdf1043022b734c7412cefdd6e64de5bfa4517ae580b0f13a3709"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THG3XM5WKAKFQSQOFTVMO6UQSY/bundle.json","state_url":"https://pith.science/pith/THG3XM5WKAKFQSQOFTVMO6UQSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THG3XM5WKAKFQSQOFTVMO6UQSY/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":"2026-08-09T00:17:42Z","links":{"resolver":"https://pith.science/pith/THG3XM5WKAKFQSQOFTVMO6UQSY","bundle":"https://pith.science/pith/THG3XM5WKAKFQSQOFTVMO6UQSY/bundle.json","state":"https://pith.science/pith/THG3XM5WKAKFQSQOFTVMO6UQSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THG3XM5WKAKFQSQOFTVMO6UQSY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:THG3XM5WKAKFQSQOFTVMO6UQSY","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":"60ecdc4acab00f190090e36d68ad93ebc2adf1fbe86ebbfb2473f716ac2cdfc2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T14:15:53Z","title_canon_sha256":"25c6778d84b4831e0649799a7f6fb423129db5332b701109ad8eedcee1c311d1"},"schema_version":"1.0","source":{"id":"2505.05269","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05269","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05269v1","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05269","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"THG3XM5WKAKF","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"pith_short_16","alias_value":"THG3XM5WKAKFQSQO","created_at":"2026-07-05T11:00:21Z"},{"alias_kind":"pith_short_8","alias_value":"THG3XM5W","created_at":"2026-07-05T11:00:21Z"}],"graph_snapshots":[{"event_id":"sha256:478e272b5ddfdf1043022b734c7412cefdd6e64de5bfa4517ae580b0f13a3709","target":"graph","created_at":"2026-07-05T11:00:21Z","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/2505.05269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The surge in digitized text data requires reliable inferential methods on observed textual patterns. This article proposes a novel two-sample text test for comparing similarity between two groups of documents. The hypothesis is whether the probabilistic mapping generating the textual data is identical across two groups of documents. The proposed test aims to assess text similarity by comparing the entropy of the documents. Entropy is estimated using neural network-based language models. The test statistic is derived from an estimation-and-inference framework, where the entropy is first approxi","authors_text":"Chen Qian, Feng Guo, Jingbin Xu, Meimei Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T14:15:53Z","title":"A Two-Sample Test of Text Generation Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05269","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":"sha256:8c088f886ac2da0839b23e061845d00ff8287d09573f54ec77eba3720e495a25","target":"record","created_at":"2026-07-05T11:00:21Z","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":"60ecdc4acab00f190090e36d68ad93ebc2adf1fbe86ebbfb2473f716ac2cdfc2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-08T14:15:53Z","title_canon_sha256":"25c6778d84b4831e0649799a7f6fb423129db5332b701109ad8eedcee1c311d1"},"schema_version":"1.0","source":{"id":"2505.05269","kind":"arxiv","version":1}},"canonical_sha256":"99cdbbb3b65014584a0e2ceac77a909611901acfe67fa4903b0962d8a7851143","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99cdbbb3b65014584a0e2ceac77a909611901acfe67fa4903b0962d8a7851143","first_computed_at":"2026-07-05T11:00:21.853863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:21.853863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"czCAaM2cOCkpqCcwz1J/kfqtx061axBc6th37WNZhDGE5olZsIdJe+ilz11VMoyfXmOPAyMdVTggq+qtTp7tBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:21.854396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05269","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c088f886ac2da0839b23e061845d00ff8287d09573f54ec77eba3720e495a25","sha256:478e272b5ddfdf1043022b734c7412cefdd6e64de5bfa4517ae580b0f13a3709"],"state_sha256":"ed7f6df0f30d25598ffb28ccd1e27d0f9ef91611322150a628a21d498d2eb08e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SavjuNVueJ/NJxhFb7JHLmqMSljCJa3RXuLPo1ZypOoiBu/jdZ0iecFUjwKYEe3zRZ4xv+1zEl4/p4nK4QFgDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:17:42.315575Z","bundle_sha256":"e3b784d9cb9e768cf1f278ac5ba3507d9b7133f421d88f4943e3b8245985ba98"}}