{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6KQKFN3THW2WOXPIILR26DIIRT","short_pith_number":"pith:6KQKFN3T","canonical_record":{"source":{"id":"2607.15238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:35:23Z","cross_cats_sorted":[],"title_canon_sha256":"37e105169cfd8f1799f7fb5769b8b064acf079f58fc610ceaa55e8189af454d2","abstract_canon_sha256":"3b0f417f8d2320b4b97aced6abe6ade82193ec1ef2e96b74f00ace78c5f51263"},"schema_version":"1.0"},"canonical_sha256":"f2a0a2b7733db5675de842e3af0d088ccebcabc8c15a928ddb7523a4590ff485","source":{"kind":"arxiv","id":"2607.15238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15238","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15238v1","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15238","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"6KQKFN3THW2W","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"6KQKFN3THW2WOXPI","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"6KQKFN3T","created_at":"2026-07-17T01:22:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6KQKFN3THW2WOXPIILR26DIIRT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:35:23Z","cross_cats_sorted":[],"title_canon_sha256":"37e105169cfd8f1799f7fb5769b8b064acf079f58fc610ceaa55e8189af454d2","abstract_canon_sha256":"3b0f417f8d2320b4b97aced6abe6ade82193ec1ef2e96b74f00ace78c5f51263"},"schema_version":"1.0"},"canonical_sha256":"f2a0a2b7733db5675de842e3af0d088ccebcabc8c15a928ddb7523a4590ff485","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:16.159782Z","signature_b64":"FK6I15V+oS8d7lgChQVdRMfYMc9NGg82D5cyCMbiGoj5oJXXJ/k+w5cT/wLtp+BXgFx5ikdpc4ne7wsMf79NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a0a2b7733db5675de842e3af0d088ccebcabc8c15a928ddb7523a4590ff485","last_reissued_at":"2026-07-17T01:22:16.159004Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:16.159004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15238","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":"2026-07-17T01:22:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nudtUZey8BP25P+X19XS0b3koHVabvnQPr05QHULoN6L0i/p2Cds8Par9FwmQUQQMZknt8b8qVIIXsa4lPTxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:41:10.563772Z"},"content_sha256":"4816011d6d54e01d2a924882e8e7cddf45a4a3ad95cd3b1cb1b269f23e398a39","schema_version":"1.0","event_id":"sha256:4816011d6d54e01d2a924882e8e7cddf45a4a3ad95cd3b1cb1b269f23e398a39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6KQKFN3THW2WOXPIILR26DIIRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Identification via Compositional Data Analysis: A Linear-Time Classifier Based on Log-Ratio Geometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Paul-Andrei Pog\\u{a}cean, Sanda-Maria Avram","submitted_at":"2026-07-16T17:35:23Z","abstract_excerpt":"Language identification is commonly addressed using either neural architectures or statistical n-gram models. Neural approaches typically require substantial computational resources, whereas classical frequency-based methods offer efficient linear-time performance, but rely on distance metrics that are not always appropriate for compositional data.\n  This work models character and bigram frequency distributions as compositional vectors constrained to the simplex and mapped via the centered log-ratio (CLR) transformation bijectively onto the $(D-1)$-dimensional zero-sum subspace of $\\mathbb{R}^"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15238","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/2607.15238/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":"2026-07-17T01:22:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j9upiM0l8Vjc7AfY+qLWYnrx6oXddW0RFmCLaveY9ou8DtZJciQ39s2D4LZjkyqv58Am5FyHrMErpl0fApw8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:41:10.564854Z"},"content_sha256":"14c3d331993d916e0b82320adafc8bf69486a5985210cd16956e654fc32cfcc6","schema_version":"1.0","event_id":"sha256:14c3d331993d916e0b82320adafc8bf69486a5985210cd16956e654fc32cfcc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KQKFN3THW2WOXPIILR26DIIRT/bundle.json","state_url":"https://pith.science/pith/6KQKFN3THW2WOXPIILR26DIIRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KQKFN3THW2WOXPIILR26DIIRT/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":"2026-08-18T13:41:10Z","links":{"resolver":"https://pith.science/pith/6KQKFN3THW2WOXPIILR26DIIRT","bundle":"https://pith.science/pith/6KQKFN3THW2WOXPIILR26DIIRT/bundle.json","state":"https://pith.science/pith/6KQKFN3THW2WOXPIILR26DIIRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KQKFN3THW2WOXPIILR26DIIRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6KQKFN3THW2WOXPIILR26DIIRT","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":"3b0f417f8d2320b4b97aced6abe6ade82193ec1ef2e96b74f00ace78c5f51263","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:35:23Z","title_canon_sha256":"37e105169cfd8f1799f7fb5769b8b064acf079f58fc610ceaa55e8189af454d2"},"schema_version":"1.0","source":{"id":"2607.15238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15238","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15238v1","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15238","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"6KQKFN3THW2W","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"6KQKFN3THW2WOXPI","created_at":"2026-07-17T01:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"6KQKFN3T","created_at":"2026-07-17T01:22:16Z"}],"graph_snapshots":[{"event_id":"sha256:14c3d331993d916e0b82320adafc8bf69486a5985210cd16956e654fc32cfcc6","target":"graph","created_at":"2026-07-17T01:22:16Z","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/2607.15238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language identification is commonly addressed using either neural architectures or statistical n-gram models. Neural approaches typically require substantial computational resources, whereas classical frequency-based methods offer efficient linear-time performance, but rely on distance metrics that are not always appropriate for compositional data.\n  This work models character and bigram frequency distributions as compositional vectors constrained to the simplex and mapped via the centered log-ratio (CLR) transformation bijectively onto the $(D-1)$-dimensional zero-sum subspace of $\\mathbb{R}^","authors_text":"Paul-Andrei Pog\\u{a}cean, Sanda-Maria Avram","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:35:23Z","title":"Language Identification via Compositional Data Analysis: A Linear-Time Classifier Based on Log-Ratio Geometry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15238","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":"sha256:4816011d6d54e01d2a924882e8e7cddf45a4a3ad95cd3b1cb1b269f23e398a39","target":"record","created_at":"2026-07-17T01:22:16Z","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":"3b0f417f8d2320b4b97aced6abe6ade82193ec1ef2e96b74f00ace78c5f51263","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:35:23Z","title_canon_sha256":"37e105169cfd8f1799f7fb5769b8b064acf079f58fc610ceaa55e8189af454d2"},"schema_version":"1.0","source":{"id":"2607.15238","kind":"arxiv","version":1}},"canonical_sha256":"f2a0a2b7733db5675de842e3af0d088ccebcabc8c15a928ddb7523a4590ff485","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2a0a2b7733db5675de842e3af0d088ccebcabc8c15a928ddb7523a4590ff485","first_computed_at":"2026-07-17T01:22:16.159004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:16.159004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FK6I15V+oS8d7lgChQVdRMfYMc9NGg82D5cyCMbiGoj5oJXXJ/k+w5cT/wLtp+BXgFx5ikdpc4ne7wsMf79NBw==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:16.159782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4816011d6d54e01d2a924882e8e7cddf45a4a3ad95cd3b1cb1b269f23e398a39","sha256:14c3d331993d916e0b82320adafc8bf69486a5985210cd16956e654fc32cfcc6"],"state_sha256":"63c3499b5f41b39302b33c4de1c2c6b7cec58902fb152fef76d84fb4c9f96912"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lBlXZc5eA9TUovmXgEeLLYzUhVON4TaHm9JOA3cOloWB47EjKQGdvXNfPnieLeU/y4VR1ISqt1vdAjYVqEXICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T13:41:10.570552Z","bundle_sha256":"3d37abeaa224a66f9ff6ebefd12a3b0d23b22dcf42a0efae7d2fe8314b851ca8"}}