{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HW6G6R4N6YVRK3CHML6C4FNMUS","short_pith_number":"pith:HW6G6R4N","canonical_record":{"source":{"id":"2505.16680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T13:46:18Z","cross_cats_sorted":["q-bio.GN","q-bio.QM"],"title_canon_sha256":"0b2bd4ac1e9d9a3a778eca464892e9542ced46afbefecf2bd0e7763bb7508a4d","abstract_canon_sha256":"4fec864f632bcccefebfde1b810aa62c134cc8bfe167ed6ac45b85ed570321b5"},"schema_version":"1.0"},"canonical_sha256":"3dbc6f478df62b156c4762fc2e15aca48e28a5e51be5726c1984c7671b781ae9","source":{"kind":"arxiv","id":"2505.16680","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16680","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16680v1","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16680","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_12","alias_value":"HW6G6R4N6YVR","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_16","alias_value":"HW6G6R4N6YVRK3CH","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_8","alias_value":"HW6G6R4N","created_at":"2026-07-05T11:07:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HW6G6R4N6YVRK3CHML6C4FNMUS","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T13:46:18Z","cross_cats_sorted":["q-bio.GN","q-bio.QM"],"title_canon_sha256":"0b2bd4ac1e9d9a3a778eca464892e9542ced46afbefecf2bd0e7763bb7508a4d","abstract_canon_sha256":"4fec864f632bcccefebfde1b810aa62c134cc8bfe167ed6ac45b85ed570321b5"},"schema_version":"1.0"},"canonical_sha256":"3dbc6f478df62b156c4762fc2e15aca48e28a5e51be5726c1984c7671b781ae9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:39.024791Z","signature_b64":"OI2hnA4u60qk75qE2+J9waYU6liYbuJ7iKyRt0bkxgqvsqOXyERlfw2isW5GWZCdByeJwYnRurso2ffGKrNsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dbc6f478df62b156c4762fc2e15aca48e28a5e51be5726c1984c7671b781ae9","last_reissued_at":"2026-07-05T11:07:39.024351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:39.024351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16680","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":"2026-07-05T11:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5l/vi8BqXxGGITOL47Zk7EJP8fMKSZm81XLnPixaQZtECvNlKxiy52dgOH3Gx9nDHQ0wlSYqOVU8/hq7iFA6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:03:06.267260Z"},"content_sha256":"cf9f4de24b343658925c2857c6860ae23b6bc270e1396164df24a3dcf1098a8f","schema_version":"1.0","event_id":"sha256:cf9f4de24b343658925c2857c6860ae23b6bc270e1396164df24a3dcf1098a8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HW6G6R4N6YVRK3CHML6C4FNMUS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Genomic Structure from $k$-mers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Carl Nettelblad, Filip Thor","submitted_at":"2025-05-22T13:46:18Z","abstract_excerpt":"Sequencing a genome to determine an individual's DNA produces an enormous number of short nucleotide subsequences known as reads, which must be reassembled to reconstruct the full genome. We present a method for analyzing this type of data using contrastive learning, in which an encoder model is trained to produce embeddings that cluster together sequences from the same genomic region. The sequential nature of genomic regions is preserved in the form of trajectories through this embedding space. Trained solely to reflect the structure of the genome, the resulting model provides a general repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16680","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/2505.16680/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":"2026-07-05T11:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ryHk9ZiH+HmiR4671xHVvl0+CC7hNO/ubfoJBDtMMLP8JQhlBrILxTOicBkWSyUNDXmqPhFbp7byzshaqEqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:03:06.267816Z"},"content_sha256":"aaac01845d0533937b9dba7085a4fe64922ac630020e65520b70981441462681","schema_version":"1.0","event_id":"sha256:aaac01845d0533937b9dba7085a4fe64922ac630020e65520b70981441462681"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HW6G6R4N6YVRK3CHML6C4FNMUS/bundle.json","state_url":"https://pith.science/pith/HW6G6R4N6YVRK3CHML6C4FNMUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HW6G6R4N6YVRK3CHML6C4FNMUS/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":"2026-08-15T06:03:06Z","links":{"resolver":"https://pith.science/pith/HW6G6R4N6YVRK3CHML6C4FNMUS","bundle":"https://pith.science/pith/HW6G6R4N6YVRK3CHML6C4FNMUS/bundle.json","state":"https://pith.science/pith/HW6G6R4N6YVRK3CHML6C4FNMUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HW6G6R4N6YVRK3CHML6C4FNMUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HW6G6R4N6YVRK3CHML6C4FNMUS","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":"4fec864f632bcccefebfde1b810aa62c134cc8bfe167ed6ac45b85ed570321b5","cross_cats_sorted":["q-bio.GN","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T13:46:18Z","title_canon_sha256":"0b2bd4ac1e9d9a3a778eca464892e9542ced46afbefecf2bd0e7763bb7508a4d"},"schema_version":"1.0","source":{"id":"2505.16680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16680","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16680v1","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16680","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_12","alias_value":"HW6G6R4N6YVR","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_16","alias_value":"HW6G6R4N6YVRK3CH","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_8","alias_value":"HW6G6R4N","created_at":"2026-07-05T11:07:39Z"}],"graph_snapshots":[{"event_id":"sha256:aaac01845d0533937b9dba7085a4fe64922ac630020e65520b70981441462681","target":"graph","created_at":"2026-07-05T11:07:39Z","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/2505.16680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequencing a genome to determine an individual's DNA produces an enormous number of short nucleotide subsequences known as reads, which must be reassembled to reconstruct the full genome. We present a method for analyzing this type of data using contrastive learning, in which an encoder model is trained to produce embeddings that cluster together sequences from the same genomic region. The sequential nature of genomic regions is preserved in the form of trajectories through this embedding space. Trained solely to reflect the structure of the genome, the resulting model provides a general repre","authors_text":"Carl Nettelblad, Filip Thor","cross_cats":["q-bio.GN","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T13:46:18Z","title":"Learning Genomic Structure from $k$-mers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16680","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:cf9f4de24b343658925c2857c6860ae23b6bc270e1396164df24a3dcf1098a8f","target":"record","created_at":"2026-07-05T11:07:39Z","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":"4fec864f632bcccefebfde1b810aa62c134cc8bfe167ed6ac45b85ed570321b5","cross_cats_sorted":["q-bio.GN","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T13:46:18Z","title_canon_sha256":"0b2bd4ac1e9d9a3a778eca464892e9542ced46afbefecf2bd0e7763bb7508a4d"},"schema_version":"1.0","source":{"id":"2505.16680","kind":"arxiv","version":1}},"canonical_sha256":"3dbc6f478df62b156c4762fc2e15aca48e28a5e51be5726c1984c7671b781ae9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dbc6f478df62b156c4762fc2e15aca48e28a5e51be5726c1984c7671b781ae9","first_computed_at":"2026-07-05T11:07:39.024351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:39.024351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OI2hnA4u60qk75qE2+J9waYU6liYbuJ7iKyRt0bkxgqvsqOXyERlfw2isW5GWZCdByeJwYnRurso2ffGKrNsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:39.024791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf9f4de24b343658925c2857c6860ae23b6bc270e1396164df24a3dcf1098a8f","sha256:aaac01845d0533937b9dba7085a4fe64922ac630020e65520b70981441462681"],"state_sha256":"1931f17e14750e46babf88f3059b8af107949a57b7165626929f65ce2dd51a57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swi+1YA+oQOIejf82QuTHLbTNqbzFxScBzIqC9iVIzEkrEKWwwn78Ssh0RmE1LpCbOGI5vXLXkcccaNoVn3lDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T06:03:06.271504Z","bundle_sha256":"5aa5ecd3db8cd1ed6b3c8b23fd801ac84c8aea66e4a76241e3da50f10f4f14e5"}}