{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U7PPHML7G47QR26VVLXZQLALW3","short_pith_number":"pith:U7PPHML7","schema_version":"1.0","canonical_sha256":"a7def3b17f373f08ebd5aaef982c0bb6e38e35a4455fa56eb6b3f88252514ff8","source":{"kind":"arxiv","id":"2506.22172","version":2},"attestation_state":"computed","paper":{"title":"Bridging Chaos Game Representations and $k$-mer Frequencies of DNA Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.FL","authors_text":"Haoze He, Lila Kari, Pablo Millan Arias","submitted_at":"2025-06-27T12:35:57Z","abstract_excerpt":"This paper establishes formal mathematical foundations linking Chaos Game Representations (CGR) of DNA sequences to their underlying $k$-mer frequencies. We prove that the Frequency CGR (FCGR) of order $k$ is mathematically equivalent to a discretization of CGR at resolution $2^k \\times 2^k$, and its vectorization corresponds to the $k$-mer frequencies of the sequence. Additionally, we characterize how symmetry transformations of CGR images correspond to specific nucleotide permutations in the originating sequences. Leveraging these insights, we introduce an algorithm that generates synthetic "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.22172","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2025-06-27T12:35:57Z","cross_cats_sorted":[],"title_canon_sha256":"d7b0d226e4b2ef0f93b6af43c0ce81dee98500183703e2b9cdf0051a3d18b51a","abstract_canon_sha256":"196d4fbe886510e97f474d583ef05298c73640f82c5219120e259b8c2470c0a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:14.715067Z","signature_b64":"rmMBIK8y3nj56GfYHs96y+H7hmS6+Z52yunkZ9670HNBABmLhni5lnSiynnh2NUOjvbKnUS28NaChAl7L9ufAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7def3b17f373f08ebd5aaef982c0bb6e38e35a4455fa56eb6b3f88252514ff8","last_reissued_at":"2026-07-05T11:29:14.714257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:14.714257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Chaos Game Representations and $k$-mer Frequencies of DNA Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.FL","authors_text":"Haoze He, Lila Kari, Pablo Millan Arias","submitted_at":"2025-06-27T12:35:57Z","abstract_excerpt":"This paper establishes formal mathematical foundations linking Chaos Game Representations (CGR) of DNA sequences to their underlying $k$-mer frequencies. We prove that the Frequency CGR (FCGR) of order $k$ is mathematically equivalent to a discretization of CGR at resolution $2^k \\times 2^k$, and its vectorization corresponds to the $k$-mer frequencies of the sequence. Additionally, we characterize how symmetry transformations of CGR images correspond to specific nucleotide permutations in the originating sequences. Leveraging these insights, we introduce an algorithm that generates synthetic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22172","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.22172/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.22172","created_at":"2026-07-05T11:29:14.714355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22172v2","created_at":"2026-07-05T11:29:14.714355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22172","created_at":"2026-07-05T11:29:14.714355+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7PPHML7G47Q","created_at":"2026-07-05T11:29:14.714355+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7PPHML7G47QR26V","created_at":"2026-07-05T11:29:14.714355+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7PPHML7","created_at":"2026-07-05T11:29:14.714355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3","json":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3.json","graph_json":"https://pith.science/api/pith-number/U7PPHML7G47QR26VVLXZQLALW3/graph.json","events_json":"https://pith.science/api/pith-number/U7PPHML7G47QR26VVLXZQLALW3/events.json","paper":"https://pith.science/paper/U7PPHML7"},"agent_actions":{"view_html":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3","download_json":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3.json","view_paper":"https://pith.science/paper/U7PPHML7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22172&json=true","fetch_graph":"https://pith.science/api/pith-number/U7PPHML7G47QR26VVLXZQLALW3/graph.json","fetch_events":"https://pith.science/api/pith-number/U7PPHML7G47QR26VVLXZQLALW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3/action/storage_attestation","attest_author":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3/action/author_attestation","sign_citation":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3/action/citation_signature","submit_replication":"https://pith.science/pith/U7PPHML7G47QR26VVLXZQLALW3/action/replication_record"}},"created_at":"2026-07-05T11:29:14.714355+00:00","updated_at":"2026-07-05T11:29:14.714355+00:00"}