{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:3G2PWLMPTUI6I5SC7JN7JPEZ4L","short_pith_number":"pith:3G2PWLMP","canonical_record":{"source":{"id":"1511.01956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.PE","submitted_at":"2015-11-05T23:46:49Z","cross_cats_sorted":[],"title_canon_sha256":"7f15b3219ac2c0a21c754a4a155d1ea47e2d7449b8769d2405d48c7602cac0e8","abstract_canon_sha256":"9bb73af64e8c523f82d6d840f71a58fd1781fc3b8233c4fef620087a8e249163"},"schema_version":"1.0"},"canonical_sha256":"d9b4fb2d8f9d11e47642fa5bf4bc99e2d8d8c7201e022a777106eef780bd9e61","source":{"kind":"arxiv","id":"1511.01956","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.01956","created_at":"2026-05-18T01:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"1511.01956v2","created_at":"2026-05-18T01:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01956","created_at":"2026-05-18T01:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"3G2PWLMPTUI6","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3G2PWLMPTUI6I5SC","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3G2PWLMP","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:3G2PWLMPTUI6I5SC7JN7JPEZ4L","target":"record","payload":{"canonical_record":{"source":{"id":"1511.01956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.PE","submitted_at":"2015-11-05T23:46:49Z","cross_cats_sorted":[],"title_canon_sha256":"7f15b3219ac2c0a21c754a4a155d1ea47e2d7449b8769d2405d48c7602cac0e8","abstract_canon_sha256":"9bb73af64e8c523f82d6d840f71a58fd1781fc3b8233c4fef620087a8e249163"},"schema_version":"1.0"},"canonical_sha256":"d9b4fb2d8f9d11e47642fa5bf4bc99e2d8d8c7201e022a777106eef780bd9e61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:53.766587Z","signature_b64":"fLjhS3gCjGrxG9SthOeHSXxwcGydNBqd0R7O/e1rfRrNE0zMlrixfwc6E9eFUcrb4u+U9OV6hX6vGj8UF/EYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9b4fb2d8f9d11e47642fa5bf4bc99e2d8d8c7201e022a777106eef780bd9e61","last_reissued_at":"2026-05-18T01:22:53.766087Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:53.766087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.01956","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YT+SH3BaJ/kBRdhn7NxB2mby+Z0lowut8w98GsOsb0xoikDYyh9+TMkd9e0NFasV2XPSbYhFd3ScWZkkSPivAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:06:54.859150Z"},"content_sha256":"079162e6743e5bc121ba305b06d82919ffa2acd7be7cd5d4ccb8e09b640849bc","schema_version":"1.0","event_id":"sha256:079162e6743e5bc121ba305b06d82919ffa2acd7be7cd5d4ccb8e09b640849bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:3G2PWLMPTUI6I5SC7JN7JPEZ4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistically-Consistent k-mer Methods for Phylogenetic Tree Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.PE","authors_text":"Elizabeth S. Allman, John A. Rhodes, Seth Sullivant","submitted_at":"2015-11-05T23:46:49Z","abstract_excerpt":"Frequencies of $k$-mers in sequences are sometimes used as a basis for inferring phylogenetic trees without first obtaining a multiple sequence alignment. We show that a standard approach of using the squared-Euclidean distance between $k$-mer vectors to approximate a tree metric can be statistically inconsistent. To remedy this, we derive model-based distance corrections for orthologous sequences without gaps, which lead to consistent tree inference. The identifiability of model parameters from $k$-mer frequencies is also studied. Finally, we report simulations showing the corrected distance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.01956","kind":"arxiv","version":2},"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":"2026-05-18T01:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYBjnaRoqD/LlX8s9ptGuTvkrnBQ6q6ddOB3Q36xGjxh5oVNeQ8f3o8FAihp2vcKOVQuQ7R7+lSWPVxHfLofCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:06:54.859889Z"},"content_sha256":"2e506182643f8dc0eb94e91b5f7024cef24e23f1a69eeb95262ade4ff078810c","schema_version":"1.0","event_id":"sha256:2e506182643f8dc0eb94e91b5f7024cef24e23f1a69eeb95262ade4ff078810c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3G2PWLMPTUI6I5SC7JN7JPEZ4L/bundle.json","state_url":"https://pith.science/pith/3G2PWLMPTUI6I5SC7JN7JPEZ4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3G2PWLMPTUI6I5SC7JN7JPEZ4L/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":"2026-06-05T22:06:54Z","links":{"resolver":"https://pith.science/pith/3G2PWLMPTUI6I5SC7JN7JPEZ4L","bundle":"https://pith.science/pith/3G2PWLMPTUI6I5SC7JN7JPEZ4L/bundle.json","state":"https://pith.science/pith/3G2PWLMPTUI6I5SC7JN7JPEZ4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3G2PWLMPTUI6I5SC7JN7JPEZ4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:3G2PWLMPTUI6I5SC7JN7JPEZ4L","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":"9bb73af64e8c523f82d6d840f71a58fd1781fc3b8233c4fef620087a8e249163","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.PE","submitted_at":"2015-11-05T23:46:49Z","title_canon_sha256":"7f15b3219ac2c0a21c754a4a155d1ea47e2d7449b8769d2405d48c7602cac0e8"},"schema_version":"1.0","source":{"id":"1511.01956","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.01956","created_at":"2026-05-18T01:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"1511.01956v2","created_at":"2026-05-18T01:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01956","created_at":"2026-05-18T01:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"3G2PWLMPTUI6","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3G2PWLMPTUI6I5SC","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3G2PWLMP","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:2e506182643f8dc0eb94e91b5f7024cef24e23f1a69eeb95262ade4ff078810c","target":"graph","created_at":"2026-05-18T01:22:53Z","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":"Frequencies of $k$-mers in sequences are sometimes used as a basis for inferring phylogenetic trees without first obtaining a multiple sequence alignment. We show that a standard approach of using the squared-Euclidean distance between $k$-mer vectors to approximate a tree metric can be statistically inconsistent. To remedy this, we derive model-based distance corrections for orthologous sequences without gaps, which lead to consistent tree inference. The identifiability of model parameters from $k$-mer frequencies is also studied. Finally, we report simulations showing the corrected distance ","authors_text":"Elizabeth S. Allman, John A. Rhodes, Seth Sullivant","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.PE","submitted_at":"2015-11-05T23:46:49Z","title":"Statistically-Consistent k-mer Methods for Phylogenetic Tree Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.01956","kind":"arxiv","version":2},"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":"sha256:079162e6743e5bc121ba305b06d82919ffa2acd7be7cd5d4ccb8e09b640849bc","target":"record","created_at":"2026-05-18T01:22:53Z","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":"9bb73af64e8c523f82d6d840f71a58fd1781fc3b8233c4fef620087a8e249163","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.PE","submitted_at":"2015-11-05T23:46:49Z","title_canon_sha256":"7f15b3219ac2c0a21c754a4a155d1ea47e2d7449b8769d2405d48c7602cac0e8"},"schema_version":"1.0","source":{"id":"1511.01956","kind":"arxiv","version":2}},"canonical_sha256":"d9b4fb2d8f9d11e47642fa5bf4bc99e2d8d8c7201e022a777106eef780bd9e61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9b4fb2d8f9d11e47642fa5bf4bc99e2d8d8c7201e022a777106eef780bd9e61","first_computed_at":"2026-05-18T01:22:53.766087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:22:53.766087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fLjhS3gCjGrxG9SthOeHSXxwcGydNBqd0R7O/e1rfRrNE0zMlrixfwc6E9eFUcrb4u+U9OV6hX6vGj8UF/EYAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:22:53.766587Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.01956","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:079162e6743e5bc121ba305b06d82919ffa2acd7be7cd5d4ccb8e09b640849bc","sha256:2e506182643f8dc0eb94e91b5f7024cef24e23f1a69eeb95262ade4ff078810c"],"state_sha256":"d631a754eb64a43825019b877e6ea7ef9daa4da1ae09edcefc87b3555fd10315"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E5gLk2XZwQaqoyDRRw5kgjEtYm8b+IqiB10KSJZEKkbdalCEL5VYc4001Xf1djqGb4xC9nnAQGa7MjXWxMoeAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T22:06:54.863310Z","bundle_sha256":"e88600f05264d1c66825f6f381de411885d222c7367a4850a537fda0cdfe391c"}}