{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VSMXC6Q3NTWZ7SKJOCKQCVY766","short_pith_number":"pith:VSMXC6Q3","canonical_record":{"source":{"id":"2507.16978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-07-22T19:28:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"57535ee7ffa0335a94c68c1da0635fc37c3be24355ca35a37e084ff5d58cd877","abstract_canon_sha256":"a4a13a40e974be4b6296e96c0c429d94e608f54bcd4ce892733c1e92074b0be4"},"schema_version":"1.0"},"canonical_sha256":"ac99717a1b6ced9fc949709501571ff7bf60b9d2abfe3a2d0c3f42aeb58537d7","source":{"kind":"arxiv","id":"2507.16978","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16978","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16978v1","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16978","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"pith_short_12","alias_value":"VSMXC6Q3NTWZ","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"pith_short_16","alias_value":"VSMXC6Q3NTWZ7SKJ","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"pith_short_8","alias_value":"VSMXC6Q3","created_at":"2026-07-05T11:41:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VSMXC6Q3NTWZ7SKJOCKQCVY766","target":"record","payload":{"canonical_record":{"source":{"id":"2507.16978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-07-22T19:28:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"57535ee7ffa0335a94c68c1da0635fc37c3be24355ca35a37e084ff5d58cd877","abstract_canon_sha256":"a4a13a40e974be4b6296e96c0c429d94e608f54bcd4ce892733c1e92074b0be4"},"schema_version":"1.0"},"canonical_sha256":"ac99717a1b6ced9fc949709501571ff7bf60b9d2abfe3a2d0c3f42aeb58537d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:59.507809Z","signature_b64":"bNlp2aa9eelKVpxj8GUHC9N47OWhUbGhZlhQs5IuleSrLltxZF63bbWHlCh25ruaSCMnR8oESycfOnP4m7nDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac99717a1b6ced9fc949709501571ff7bf60b9d2abfe3a2d0c3f42aeb58537d7","last_reissued_at":"2026-07-05T11:41:59.507348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:59.507348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.16978","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":"2026-07-05T11:41:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qetWfIYvv1f2Bk3Qg4g8XZpB+YwhsC0t2ojkGJt/MSVfBk19Pq6qJ85+vcXhf27zXJ/YtvJVFMTUy6DK7UUcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:30:45.227843Z"},"content_sha256":"1e424cf038372c9dd8f30cbf7e5c68ebb126bafc860fc7a05829e0ac3ff45f2d","schema_version":"1.0","event_id":"sha256:1e424cf038372c9dd8f30cbf7e5c68ebb126bafc860fc7a05829e0ac3ff45f2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VSMXC6Q3NTWZ7SKJOCKQCVY766","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast and Scalable Gene Embedding Search: A Comparative Study of FAISS and ScaNN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Bahrad A. Sokhansanj, Gail Rosen, Gavin Hearne, Harrison Muller, James R. Brown, Kieran Lynch, Mohammad Saleh Refahi","submitted_at":"2025-07-22T19:28:54Z","abstract_excerpt":"The exponential growth of DNA sequencing data has outpaced traditional heuristic-based methods, which struggle to scale effectively. Efficient computational approaches are urgently needed to support large-scale similarity search, a foundational task in bioinformatics for detecting homology, functional similarity, and novelty among genomic and proteomic sequences. Although tools like BLAST have been widely used and remain effective in many scenarios, they suffer from limitations such as high computational cost and poor performance on divergent sequences.\n  In this work, we explore embedding-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16978","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/2507.16978/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":"2026-07-05T11:41:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Izqx3+AFe5Pw4xZx37XJA5sjj0aYAUzDn9H54/TLeB2KjKEOANeKzHL076sPLpaOQfNd4HPOJk1Chlkz/yGdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:30:45.228560Z"},"content_sha256":"bf9acae32a0fbf3f6a9676a8f90d7213fe05c5b54f45be5b34dc125b4404e012","schema_version":"1.0","event_id":"sha256:bf9acae32a0fbf3f6a9676a8f90d7213fe05c5b54f45be5b34dc125b4404e012"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSMXC6Q3NTWZ7SKJOCKQCVY766/bundle.json","state_url":"https://pith.science/pith/VSMXC6Q3NTWZ7SKJOCKQCVY766/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSMXC6Q3NTWZ7SKJOCKQCVY766/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":"2026-08-09T22:30:45Z","links":{"resolver":"https://pith.science/pith/VSMXC6Q3NTWZ7SKJOCKQCVY766","bundle":"https://pith.science/pith/VSMXC6Q3NTWZ7SKJOCKQCVY766/bundle.json","state":"https://pith.science/pith/VSMXC6Q3NTWZ7SKJOCKQCVY766/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSMXC6Q3NTWZ7SKJOCKQCVY766/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VSMXC6Q3NTWZ7SKJOCKQCVY766","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":"a4a13a40e974be4b6296e96c0c429d94e608f54bcd4ce892733c1e92074b0be4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-07-22T19:28:54Z","title_canon_sha256":"57535ee7ffa0335a94c68c1da0635fc37c3be24355ca35a37e084ff5d58cd877"},"schema_version":"1.0","source":{"id":"2507.16978","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16978","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16978v1","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16978","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"pith_short_12","alias_value":"VSMXC6Q3NTWZ","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"pith_short_16","alias_value":"VSMXC6Q3NTWZ7SKJ","created_at":"2026-07-05T11:41:59Z"},{"alias_kind":"pith_short_8","alias_value":"VSMXC6Q3","created_at":"2026-07-05T11:41:59Z"}],"graph_snapshots":[{"event_id":"sha256:bf9acae32a0fbf3f6a9676a8f90d7213fe05c5b54f45be5b34dc125b4404e012","target":"graph","created_at":"2026-07-05T11:41:59Z","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/2507.16978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The exponential growth of DNA sequencing data has outpaced traditional heuristic-based methods, which struggle to scale effectively. Efficient computational approaches are urgently needed to support large-scale similarity search, a foundational task in bioinformatics for detecting homology, functional similarity, and novelty among genomic and proteomic sequences. Although tools like BLAST have been widely used and remain effective in many scenarios, they suffer from limitations such as high computational cost and poor performance on divergent sequences.\n  In this work, we explore embedding-bas","authors_text":"Bahrad A. Sokhansanj, Gail Rosen, Gavin Hearne, Harrison Muller, James R. Brown, Kieran Lynch, Mohammad Saleh Refahi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-07-22T19:28:54Z","title":"Fast and Scalable Gene Embedding Search: A Comparative Study of FAISS and ScaNN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16978","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":"sha256:1e424cf038372c9dd8f30cbf7e5c68ebb126bafc860fc7a05829e0ac3ff45f2d","target":"record","created_at":"2026-07-05T11:41:59Z","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":"a4a13a40e974be4b6296e96c0c429d94e608f54bcd4ce892733c1e92074b0be4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-07-22T19:28:54Z","title_canon_sha256":"57535ee7ffa0335a94c68c1da0635fc37c3be24355ca35a37e084ff5d58cd877"},"schema_version":"1.0","source":{"id":"2507.16978","kind":"arxiv","version":1}},"canonical_sha256":"ac99717a1b6ced9fc949709501571ff7bf60b9d2abfe3a2d0c3f42aeb58537d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac99717a1b6ced9fc949709501571ff7bf60b9d2abfe3a2d0c3f42aeb58537d7","first_computed_at":"2026-07-05T11:41:59.507348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:59.507348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bNlp2aa9eelKVpxj8GUHC9N47OWhUbGhZlhQs5IuleSrLltxZF63bbWHlCh25ruaSCMnR8oESycfOnP4m7nDCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:59.507809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.16978","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e424cf038372c9dd8f30cbf7e5c68ebb126bafc860fc7a05829e0ac3ff45f2d","sha256:bf9acae32a0fbf3f6a9676a8f90d7213fe05c5b54f45be5b34dc125b4404e012"],"state_sha256":"843ade35b649a2a428fdeaf79b4d0aebef9802d3fec251634045685d64b58268"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XEXwn8YjqigjaParviKAUNqYSGI2KGEqx0sRv8Yfg7yVA90unMkUCAR2Vi9Uh5qLVZ0j+noO1ds6J22rWbwWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:30:45.235400Z","bundle_sha256":"13a5c255587341b77bf52bd58a6f05dce92fbd392930b7629035818c24717c49"}}