{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3FUWOAMXYZSSNZLADU2LMQY436","short_pith_number":"pith:3FUWOAMX","schema_version":"1.0","canonical_sha256":"d969670197c66526e5601d34b6431cdf9b9553079b974a960fca205876139633","source":{"kind":"arxiv","id":"2606.04171","version":1},"attestation_state":"computed","paper":{"title":"MimeLens: Position-Agnostic Content-Type Detection for Binary Fragments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael J. Bommarito II","submitted_at":"2026-06-02T19:35:44Z","abstract_excerpt":"File-type classification underlies many workflows like malware triage, forensic carving, packet inspection, and storage indexing. Learned systems such as Google's Magika assume whole-file access at a known offset, so they break on the inputs many of these tasks actually produce, like a single packet payload, a header-less carved fragment, a random disk block, or a chunked upload. We introduce MimeLens, a family of small BERT-style encoders pretrained on binary content from windows sampled at a uniformly random offset within each file, with no privileged head-of-file position, in standard- and "},"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":"2606.04171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T19:35:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5ea0646352bba31c3a7cc5a48fdf29f154ba81b6c11aeacd9ab381160eb48fce","abstract_canon_sha256":"b5f1f11e2981964d29ccec0fe289a5d689e93c451549ce2727e59e6eacc81970"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:18.792768Z","signature_b64":"c5pAQEFaMbEFv+7z9YfH+dVlkXIyAJpsAg8EtMMIxj8CN4icvXNKiassMQr330eOPTBRywUc/5ZZgw6jSb3UAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d969670197c66526e5601d34b6431cdf9b9553079b974a960fca205876139633","last_reissued_at":"2026-06-04T01:08:18.791716Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:18.791716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MimeLens: Position-Agnostic Content-Type Detection for Binary Fragments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael J. Bommarito II","submitted_at":"2026-06-02T19:35:44Z","abstract_excerpt":"File-type classification underlies many workflows like malware triage, forensic carving, packet inspection, and storage indexing. Learned systems such as Google's Magika assume whole-file access at a known offset, so they break on the inputs many of these tasks actually produce, like a single packet payload, a header-less carved fragment, a random disk block, or a chunked upload. We introduce MimeLens, a family of small BERT-style encoders pretrained on binary content from windows sampled at a uniformly random offset within each file, with no privileged head-of-file position, in standard- and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04171","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/2606.04171/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":"2606.04171","created_at":"2026-06-04T01:08:18.791906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04171v1","created_at":"2026-06-04T01:08:18.791906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04171","created_at":"2026-06-04T01:08:18.791906+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FUWOAMXYZSS","created_at":"2026-06-04T01:08:18.791906+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FUWOAMXYZSSNZLA","created_at":"2026-06-04T01:08:18.791906+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FUWOAMX","created_at":"2026-06-04T01:08:18.791906+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/3FUWOAMXYZSSNZLADU2LMQY436","json":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436.json","graph_json":"https://pith.science/api/pith-number/3FUWOAMXYZSSNZLADU2LMQY436/graph.json","events_json":"https://pith.science/api/pith-number/3FUWOAMXYZSSNZLADU2LMQY436/events.json","paper":"https://pith.science/paper/3FUWOAMX"},"agent_actions":{"view_html":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436","download_json":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436.json","view_paper":"https://pith.science/paper/3FUWOAMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04171&json=true","fetch_graph":"https://pith.science/api/pith-number/3FUWOAMXYZSSNZLADU2LMQY436/graph.json","fetch_events":"https://pith.science/api/pith-number/3FUWOAMXYZSSNZLADU2LMQY436/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/action/storage_attestation","attest_author":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/action/author_attestation","sign_citation":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/action/citation_signature","submit_replication":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/action/replication_record"}},"created_at":"2026-06-04T01:08:18.791906+00:00","updated_at":"2026-06-04T01:08:18.791906+00:00"}