{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:F6YNIRJ7LZXNF5LWPETGYSIUN4","short_pith_number":"pith:F6YNIRJ7","canonical_record":{"source":{"id":"2607.01601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"2ba43cd6dc982207f15ab302a089d049778bdd84238878063af8002b75610368","abstract_canon_sha256":"877d3f9a37d922901bda9f95e164d5e61a81c8bd359e94f4f7055d73c567bab0"},"schema_version":"1.0"},"canonical_sha256":"2fb0d4453f5e6ed2f57679266c49146f36eb27d5e2c1c9fc214010edec229a6b","source":{"kind":"arxiv","id":"2607.01601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01601","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01601v1","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01601","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"F6YNIRJ7LZXN","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"F6YNIRJ7LZXNF5LW","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"F6YNIRJ7","created_at":"2026-07-03T01:17:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:F6YNIRJ7LZXNF5LWPETGYSIUN4","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"2ba43cd6dc982207f15ab302a089d049778bdd84238878063af8002b75610368","abstract_canon_sha256":"877d3f9a37d922901bda9f95e164d5e61a81c8bd359e94f4f7055d73c567bab0"},"schema_version":"1.0"},"canonical_sha256":"2fb0d4453f5e6ed2f57679266c49146f36eb27d5e2c1c9fc214010edec229a6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:03.005845Z","signature_b64":"ajD9LGzI8JsgP+9OBLfmjjINNc7EYnR1T4r/ocwf6EaujAkzKUiKEO2/c9q6UXNoU5RGKd14ndKTsOBEJjfYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fb0d4453f5e6ed2f57679266c49146f36eb27d5e2c1c9fc214010edec229a6b","last_reissued_at":"2026-07-03T01:17:03.005389Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:03.005389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01601","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":"2026-07-03T01:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P8nV3Va5sEk6PbrdHpowqcDx0ecteO85MqqBvJrjIZX0AMAtm3EOedMIY3oTcMXfRvWs2USAgVaAO7YsZJYSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T14:46:25.232846Z"},"content_sha256":"a736ba7bef73898f213666d3fdb099a6f7623c92a85cbc64c7f21e9791051856","schema_version":"1.0","event_id":"sha256:a736ba7bef73898f213666d3fdb099a6f7623c92a85cbc64c7f21e9791051856"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:F6YNIRJ7LZXNF5LWPETGYSIUN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiabei Liu, Kejian Tong, Tao Ning, Xinyi Fang, Yuhang He","submitted_at":"2026-07-02T02:00:06Z","abstract_excerpt":"Large scale document deduplication must preserve semantic equivalence while remaining efficient over massive corpora. We present SemHash LLM, a multi granularity framework that unifies semantic projection hashing, attention weighted MinHash, contrastive boundary learning, and selective LLM based adjudication. The method combines character, token, and document level signals through gated fusion, then applies a cascaded filtering pipeline for efficient candidate reduction. Semantic projection hashing learns compact binary codes in distilled LLM embedding space, while attention weighted Min- Hash"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01601","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/2607.01601/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":"2026-07-03T01:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIti1Y6LWLgWE8Rdy42Bn1tZglmOnHqsv6HK83x4RHr2Ls7F7SlL/jWWhQvxuPzfA/AnDMKLMWyeXj51wU/KAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T14:46:25.233214Z"},"content_sha256":"13437c4968648b832caec01daec1694795b89f0b8ddbccb0f4583677ac5d52b8","schema_version":"1.0","event_id":"sha256:13437c4968648b832caec01daec1694795b89f0b8ddbccb0f4583677ac5d52b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F6YNIRJ7LZXNF5LWPETGYSIUN4/bundle.json","state_url":"https://pith.science/pith/F6YNIRJ7LZXNF5LWPETGYSIUN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F6YNIRJ7LZXNF5LWPETGYSIUN4/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":"2026-07-19T14:46:25Z","links":{"resolver":"https://pith.science/pith/F6YNIRJ7LZXNF5LWPETGYSIUN4","bundle":"https://pith.science/pith/F6YNIRJ7LZXNF5LWPETGYSIUN4/bundle.json","state":"https://pith.science/pith/F6YNIRJ7LZXNF5LWPETGYSIUN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F6YNIRJ7LZXNF5LWPETGYSIUN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F6YNIRJ7LZXNF5LWPETGYSIUN4","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":"877d3f9a37d922901bda9f95e164d5e61a81c8bd359e94f4f7055d73c567bab0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:00:06Z","title_canon_sha256":"2ba43cd6dc982207f15ab302a089d049778bdd84238878063af8002b75610368"},"schema_version":"1.0","source":{"id":"2607.01601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01601","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01601v1","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01601","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"F6YNIRJ7LZXN","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"F6YNIRJ7LZXNF5LW","created_at":"2026-07-03T01:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"F6YNIRJ7","created_at":"2026-07-03T01:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:13437c4968648b832caec01daec1694795b89f0b8ddbccb0f4583677ac5d52b8","target":"graph","created_at":"2026-07-03T01:17:03Z","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/2607.01601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large scale document deduplication must preserve semantic equivalence while remaining efficient over massive corpora. We present SemHash LLM, a multi granularity framework that unifies semantic projection hashing, attention weighted MinHash, contrastive boundary learning, and selective LLM based adjudication. The method combines character, token, and document level signals through gated fusion, then applies a cascaded filtering pipeline for efficient candidate reduction. Semantic projection hashing learns compact binary codes in distilled LLM embedding space, while attention weighted Min- Hash","authors_text":"Jiabei Liu, Kejian Tong, Tao Ning, Xinyi Fang, Yuhang He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:00:06Z","title":"SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01601","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:a736ba7bef73898f213666d3fdb099a6f7623c92a85cbc64c7f21e9791051856","target":"record","created_at":"2026-07-03T01:17:03Z","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":"877d3f9a37d922901bda9f95e164d5e61a81c8bd359e94f4f7055d73c567bab0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T02:00:06Z","title_canon_sha256":"2ba43cd6dc982207f15ab302a089d049778bdd84238878063af8002b75610368"},"schema_version":"1.0","source":{"id":"2607.01601","kind":"arxiv","version":1}},"canonical_sha256":"2fb0d4453f5e6ed2f57679266c49146f36eb27d5e2c1c9fc214010edec229a6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fb0d4453f5e6ed2f57679266c49146f36eb27d5e2c1c9fc214010edec229a6b","first_computed_at":"2026-07-03T01:17:03.005389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:03.005389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ajD9LGzI8JsgP+9OBLfmjjINNc7EYnR1T4r/ocwf6EaujAkzKUiKEO2/c9q6UXNoU5RGKd14ndKTsOBEJjfYAQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:03.005845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a736ba7bef73898f213666d3fdb099a6f7623c92a85cbc64c7f21e9791051856","sha256:13437c4968648b832caec01daec1694795b89f0b8ddbccb0f4583677ac5d52b8"],"state_sha256":"742f2b99d07e25729db459f4dacc5c02da87f20b7aa94a55affa6ddbdace8e1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fBCWC9jR6jvv+9ZRhW2psplz9RG91dm9biy9v09QmH6JooJ06v/Li1i4RrK2NwUcmDJ/0Q/1h0+C2DObDamLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T14:46:25.235268Z","bundle_sha256":"15c52b43fa60a22fca24ec53f98236f6fcf1c334894bf56d23a9a2d7ec25858a"}}