{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QHNC7I4ASPB2JTSNOMLUCBADWT","short_pith_number":"pith:QHNC7I4A","canonical_record":{"source":{"id":"2607.08382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-09T12:01:40Z","cross_cats_sorted":[],"title_canon_sha256":"8e62a1d63aa39c0283ed3a51f47002496cc57e894aff2408c60634ef23e9a2dc","abstract_canon_sha256":"9e1ec03f178f5dc8bfbd6a1c22f92048a2534c55793b32aeb5f3bc57ea933edb"},"schema_version":"1.0"},"canonical_sha256":"81da2fa38093c3a4ce4d7317410403b4d855df9a1159ae2ad6f0c400edade731","source":{"kind":"arxiv","id":"2607.08382","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08382","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08382v1","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08382","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"pith_short_12","alias_value":"QHNC7I4ASPB2","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"pith_short_16","alias_value":"QHNC7I4ASPB2JTSN","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"pith_short_8","alias_value":"QHNC7I4A","created_at":"2026-07-10T01:19:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QHNC7I4ASPB2JTSNOMLUCBADWT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.08382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-09T12:01:40Z","cross_cats_sorted":[],"title_canon_sha256":"8e62a1d63aa39c0283ed3a51f47002496cc57e894aff2408c60634ef23e9a2dc","abstract_canon_sha256":"9e1ec03f178f5dc8bfbd6a1c22f92048a2534c55793b32aeb5f3bc57ea933edb"},"schema_version":"1.0"},"canonical_sha256":"81da2fa38093c3a4ce4d7317410403b4d855df9a1159ae2ad6f0c400edade731","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:48.641947Z","signature_b64":"gw1ThEth4sEFTKzCgUyJkINIt1clPgQ77bq2HwFn61xlbb96qty++XVUoo6xDooi9m9ViCl/EqzorMkh/cz6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81da2fa38093c3a4ce4d7317410403b4d855df9a1159ae2ad6f0c400edade731","last_reissued_at":"2026-07-10T01:19:48.641519Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:48.641519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.08382","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":"2026-07-10T01:19:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oIPA6El6CEkJyXEb8ciLgs5hnV9Gc20ZgsYHwskBY01k2QcRAZA7ApXHzUZ/mznb8/FUhgfy1KBewqOv3DB/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T09:12:42.723173Z"},"content_sha256":"833c4508b3d59dea2ac9dd31e238f91ad3e80e8975cd4c7297a322f1636e5412","schema_version":"1.0","event_id":"sha256:833c4508b3d59dea2ac9dd31e238f91ad3e80e8975cd4c7297a322f1636e5412"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QHNC7I4ASPB2JTSNOMLUCBADWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"H3D: Benchmarking Unsupervised Text Hashing for Fine-Grained Document Deduplication","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Li, Hanwen Hao, Jiaxun Lyu, Jingzheng Li, Junnan Liu, Qianren Mao, Zhijun Chen","submitted_at":"2026-07-09T12:01:40Z","abstract_excerpt":"Document hashing provides compact representations for efficient similarity search and document deduplication, but existing studies rarely compare hashing pipelines under a unified protocol for fine-grained scientific documents. H3D is an unsupervised text hashing benchmark for fine-grained document deduplication. It evaluates representative unsupervised non-learning hashing approaches (MinHash, SimHash, Winnowing, FuzzyHash, FlyHash) together with semantic-sensitive methods built from frozen BGE embeddings and two quantization strategies (BGE-BIHash and BGE-LSHash). The non-learning methods ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08382","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/2607.08382/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":"2026-07-10T01:19:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F8v6Mubu5vrAuWyBdy2G+NlqHYT29F3aRimKwdi1r8HwXqZgwKaWhnBoptIIf0YSRYtRFm7bXd9It6SxBWHxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T09:12:42.723561Z"},"content_sha256":"dfad96a85128b9867887ae68f51aa59091c738067a169f9dd6bd34f82008b30c","schema_version":"1.0","event_id":"sha256:dfad96a85128b9867887ae68f51aa59091c738067a169f9dd6bd34f82008b30c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHNC7I4ASPB2JTSNOMLUCBADWT/bundle.json","state_url":"https://pith.science/pith/QHNC7I4ASPB2JTSNOMLUCBADWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHNC7I4ASPB2JTSNOMLUCBADWT/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":"2026-07-25T09:12:42Z","links":{"resolver":"https://pith.science/pith/QHNC7I4ASPB2JTSNOMLUCBADWT","bundle":"https://pith.science/pith/QHNC7I4ASPB2JTSNOMLUCBADWT/bundle.json","state":"https://pith.science/pith/QHNC7I4ASPB2JTSNOMLUCBADWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHNC7I4ASPB2JTSNOMLUCBADWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QHNC7I4ASPB2JTSNOMLUCBADWT","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":"9e1ec03f178f5dc8bfbd6a1c22f92048a2534c55793b32aeb5f3bc57ea933edb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-09T12:01:40Z","title_canon_sha256":"8e62a1d63aa39c0283ed3a51f47002496cc57e894aff2408c60634ef23e9a2dc"},"schema_version":"1.0","source":{"id":"2607.08382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08382","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08382v1","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08382","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"pith_short_12","alias_value":"QHNC7I4ASPB2","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"pith_short_16","alias_value":"QHNC7I4ASPB2JTSN","created_at":"2026-07-10T01:19:48Z"},{"alias_kind":"pith_short_8","alias_value":"QHNC7I4A","created_at":"2026-07-10T01:19:48Z"}],"graph_snapshots":[{"event_id":"sha256:dfad96a85128b9867887ae68f51aa59091c738067a169f9dd6bd34f82008b30c","target":"graph","created_at":"2026-07-10T01:19:48Z","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/2607.08382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document hashing provides compact representations for efficient similarity search and document deduplication, but existing studies rarely compare hashing pipelines under a unified protocol for fine-grained scientific documents. H3D is an unsupervised text hashing benchmark for fine-grained document deduplication. It evaluates representative unsupervised non-learning hashing approaches (MinHash, SimHash, Winnowing, FuzzyHash, FlyHash) together with semantic-sensitive methods built from frozen BGE embeddings and two quantization strategies (BGE-BIHash and BGE-LSHash). The non-learning methods ge","authors_text":"Bo Li, Hanwen Hao, Jiaxun Lyu, Jingzheng Li, Junnan Liu, Qianren Mao, Zhijun Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-09T12:01:40Z","title":"H3D: Benchmarking Unsupervised Text Hashing for Fine-Grained Document Deduplication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08382","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":"sha256:833c4508b3d59dea2ac9dd31e238f91ad3e80e8975cd4c7297a322f1636e5412","target":"record","created_at":"2026-07-10T01:19:48Z","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":"9e1ec03f178f5dc8bfbd6a1c22f92048a2534c55793b32aeb5f3bc57ea933edb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-09T12:01:40Z","title_canon_sha256":"8e62a1d63aa39c0283ed3a51f47002496cc57e894aff2408c60634ef23e9a2dc"},"schema_version":"1.0","source":{"id":"2607.08382","kind":"arxiv","version":1}},"canonical_sha256":"81da2fa38093c3a4ce4d7317410403b4d855df9a1159ae2ad6f0c400edade731","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81da2fa38093c3a4ce4d7317410403b4d855df9a1159ae2ad6f0c400edade731","first_computed_at":"2026-07-10T01:19:48.641519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:48.641519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gw1ThEth4sEFTKzCgUyJkINIt1clPgQ77bq2HwFn61xlbb96qty++XVUoo6xDooi9m9ViCl/EqzorMkh/cz6Bg==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:48.641947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:833c4508b3d59dea2ac9dd31e238f91ad3e80e8975cd4c7297a322f1636e5412","sha256:dfad96a85128b9867887ae68f51aa59091c738067a169f9dd6bd34f82008b30c"],"state_sha256":"cc34a557fa692b57d7bb9e2684f80fd16204a6047ff35cd2084d1aaf1afbda93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mjrZeeczRKBMUz7CWMVcByOutnkVg1iNg9vXJsdc4BelK+vjs3p6dpaQKlC416hu09tzEsGBCZUYv7JFg9AABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T09:12:42.726147Z","bundle_sha256":"a90132bfc3b96ac60b649dffea281cf49905d6db451a982acdb7cf1a00751ff4"}}