{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6KNKPTLXQG7SZ65LFXESLUYN45","short_pith_number":"pith:6KNKPTLX","canonical_record":{"source":{"id":"1805.03771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2018-05-10T01:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"689cd634f2a466692551b79a1095820f16c502a0eb1829bc5b3f8f7720a2d93a","abstract_canon_sha256":"21e0115f3b22df238fa2c3d0eac4330ffbfc7253eaae085980c67a6bc1dd712c"},"schema_version":"1.0"},"canonical_sha256":"f29aa7cd7781bf2cfbab2dc925d30de773c5c7c5b2ea55f4fed43bf5b54d679b","source":{"kind":"arxiv","id":"1805.03771","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03771","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03771v1","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03771","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"6KNKPTLXQG7S","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6KNKPTLXQG7SZ65L","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6KNKPTLX","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6KNKPTLXQG7SZ65LFXESLUYN45","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2018-05-10T01:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"689cd634f2a466692551b79a1095820f16c502a0eb1829bc5b3f8f7720a2d93a","abstract_canon_sha256":"21e0115f3b22df238fa2c3d0eac4330ffbfc7253eaae085980c67a6bc1dd712c"},"schema_version":"1.0"},"canonical_sha256":"f29aa7cd7781bf2cfbab2dc925d30de773c5c7c5b2ea55f4fed43bf5b54d679b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:18.822517Z","signature_b64":"VrMTEivgzXkZ9tUgvmoxEXht4j//7W/eB5n/Mo3tBSzqPJbWeK17f/rCAdBnT97IoqEjisfQhEpH4ciHZ3zzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f29aa7cd7781bf2cfbab2dc925d30de773c5c7c5b2ea55f4fed43bf5b54d679b","last_reissued_at":"2026-05-18T00:16:18.822073Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:18.822073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03771","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":"2026-05-18T00:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wCYi/WE9ViDrauMWxWyHT4R5Bny9sjiWk2uXGUiQYtxQ+p8Zsu65LbL+cAyxyuG4PGrYkQzL3ktT4krSjyBQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T09:21:15.207150Z"},"content_sha256":"5887c61faf7757414faf9e8ea4f657a861916d2819669fe282d38f5c8854c8ca","schema_version":"1.0","event_id":"sha256:5887c61faf7757414faf9e8ea4f657a861916d2819669fe282d38f5c8854c8ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6KNKPTLXQG7SZ65LFXESLUYN45","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transcription Factor-DNA Binding Via Machine Learning Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Charles Delisi, Mark Kon, Yue Fan","submitted_at":"2018-05-10T01:13:44Z","abstract_excerpt":"We present ensemble methods in a machine learning (ML) framework combining predictions from five known motif/binding site exploration algorithms. For a given TF the ensemble starts with position weight matrices (PWM's) for the motif, collected from the component algorithms. Using dimension reduction, we identify significant PWM-based subspaces for analysis. Within each subspace a machine classifier is built for identifying the TF's gene (promoter) targets (Problem 1). These PWM-based subspaces form an ML-based sequence analysis tool. Problem 2 (finding binding motifs) is solved by agglomeratin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03771","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":""},"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":"2026-05-18T00:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJvLsLWWFf8FkQZk5v9gWx0stAdo3/Omyn4u0rEsoLEpXwoL75ZkYmV+ewJqAXyE4vWH+lM/mhUGwdUDLE0pDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T09:21:15.207510Z"},"content_sha256":"f6b6b5e9d0a634253bb6a3aaf65ae450af53bd7e871c3bb8e4f2ab175c159566","schema_version":"1.0","event_id":"sha256:f6b6b5e9d0a634253bb6a3aaf65ae450af53bd7e871c3bb8e4f2ab175c159566"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/bundle.json","state_url":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KNKPTLXQG7SZ65LFXESLUYN45/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":"2026-06-24T09:21:15Z","links":{"resolver":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45","bundle":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/bundle.json","state":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KNKPTLXQG7SZ65LFXESLUYN45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6KNKPTLXQG7SZ65LFXESLUYN45","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":"21e0115f3b22df238fa2c3d0eac4330ffbfc7253eaae085980c67a6bc1dd712c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2018-05-10T01:13:44Z","title_canon_sha256":"689cd634f2a466692551b79a1095820f16c502a0eb1829bc5b3f8f7720a2d93a"},"schema_version":"1.0","source":{"id":"1805.03771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03771","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03771v1","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03771","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"6KNKPTLXQG7S","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6KNKPTLXQG7SZ65L","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6KNKPTLX","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:f6b6b5e9d0a634253bb6a3aaf65ae450af53bd7e871c3bb8e4f2ab175c159566","target":"graph","created_at":"2026-05-18T00:16:18Z","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"},"paper":{"abstract_excerpt":"We present ensemble methods in a machine learning (ML) framework combining predictions from five known motif/binding site exploration algorithms. For a given TF the ensemble starts with position weight matrices (PWM's) for the motif, collected from the component algorithms. Using dimension reduction, we identify significant PWM-based subspaces for analysis. Within each subspace a machine classifier is built for identifying the TF's gene (promoter) targets (Problem 1). These PWM-based subspaces form an ML-based sequence analysis tool. Problem 2 (finding binding motifs) is solved by agglomeratin","authors_text":"Charles Delisi, Mark Kon, Yue Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2018-05-10T01:13:44Z","title":"Transcription Factor-DNA Binding Via Machine Learning Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03771","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":"sha256:5887c61faf7757414faf9e8ea4f657a861916d2819669fe282d38f5c8854c8ca","target":"record","created_at":"2026-05-18T00:16:18Z","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":"21e0115f3b22df238fa2c3d0eac4330ffbfc7253eaae085980c67a6bc1dd712c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2018-05-10T01:13:44Z","title_canon_sha256":"689cd634f2a466692551b79a1095820f16c502a0eb1829bc5b3f8f7720a2d93a"},"schema_version":"1.0","source":{"id":"1805.03771","kind":"arxiv","version":1}},"canonical_sha256":"f29aa7cd7781bf2cfbab2dc925d30de773c5c7c5b2ea55f4fed43bf5b54d679b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f29aa7cd7781bf2cfbab2dc925d30de773c5c7c5b2ea55f4fed43bf5b54d679b","first_computed_at":"2026-05-18T00:16:18.822073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:18.822073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VrMTEivgzXkZ9tUgvmoxEXht4j//7W/eB5n/Mo3tBSzqPJbWeK17f/rCAdBnT97IoqEjisfQhEpH4ciHZ3zzCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:18.822517Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5887c61faf7757414faf9e8ea4f657a861916d2819669fe282d38f5c8854c8ca","sha256:f6b6b5e9d0a634253bb6a3aaf65ae450af53bd7e871c3bb8e4f2ab175c159566"],"state_sha256":"fcef6dc31eb09925b9fcc8ae228971bf43e9260b1bec5786940fdd3ddadb2f5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HEXSinIemNMOAUWSl/j6aTUlLSrTn3c2Ih8OE7ZmmZq0C2LiCbbzX+bjCZ+OGjbpek1na78gnIiAmdENzEqGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T09:21:15.209442Z","bundle_sha256":"2bdaf29c80eab3e1f7922b23124f368f264002323992a82f665850a2c66807b2"}}