{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SXZ7DJHGV7M53TNEEHRKVCYD24","short_pith_number":"pith:SXZ7DJHG","schema_version":"1.0","canonical_sha256":"95f3f1a4e6afd9ddcda421e2aa8b03d702a70b04b41c2e5038384d87a83df3e7","source":{"kind":"arxiv","id":"2605.21615","version":1},"attestation_state":"computed","paper":{"title":"ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CR","authors_text":"Chang Liu, Edward Raff, James Holt, Kristopher Micinski, Nicol\\`o Altamura, Noah Fleischmann","submitted_at":"2026-05-20T18:23:17Z","abstract_excerpt":"Existing binary corpora typically capture only one or two axes of binary variation: they either provide cross-compiler builds without a temporal axis, or CVE labels for single-build binaries. None combine cross-build diversity, cross-version history, and CVE labels into a queryable structure. We present ASSEMBLAGE-DEEPHISTORY, which consolidates these dimensions into a unified framework where every binary's compilation context, source code, vulnerable functions, and package version are stored as first-class metadata.\n  ASSEMBLAGE-DEEPHISTORY comprises 73,610 binaries spanning 248 open-source p"},"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":"2605.21615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-20T18:23:17Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"5a9ff1326e036aec38a77ae59deca1ac4b86cd94bf5b646f551964eed9576818","abstract_canon_sha256":"4d1f6eb1ce41689816d8b816a4c22dba3cb5f2613cf2c8e98ffe4dc018f21ce9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:25.507901Z","signature_b64":"cXrA3BZblyfizO0HpMn2xG0yMiGIelyHLOoQCRNp9C0gN3EJttgz+2OWAQThYrv/oity6DElSvCjR2bd8PArBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f3f1a4e6afd9ddcda421e2aa8b03d702a70b04b41c2e5038384d87a83df3e7","last_reissued_at":"2026-05-22T01:03:25.507120Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:25.507120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CR","authors_text":"Chang Liu, Edward Raff, James Holt, Kristopher Micinski, Nicol\\`o Altamura, Noah Fleischmann","submitted_at":"2026-05-20T18:23:17Z","abstract_excerpt":"Existing binary corpora typically capture only one or two axes of binary variation: they either provide cross-compiler builds without a temporal axis, or CVE labels for single-build binaries. None combine cross-build diversity, cross-version history, and CVE labels into a queryable structure. We present ASSEMBLAGE-DEEPHISTORY, which consolidates these dimensions into a unified framework where every binary's compilation context, source code, vulnerable functions, and package version are stored as first-class metadata.\n  ASSEMBLAGE-DEEPHISTORY comprises 73,610 binaries spanning 248 open-source p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21615","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/2605.21615/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":"2605.21615","created_at":"2026-05-22T01:03:25.507232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21615v1","created_at":"2026-05-22T01:03:25.507232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21615","created_at":"2026-05-22T01:03:25.507232+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXZ7DJHGV7M5","created_at":"2026-05-22T01:03:25.507232+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXZ7DJHGV7M53TNE","created_at":"2026-05-22T01:03:25.507232+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXZ7DJHG","created_at":"2026-05-22T01:03:25.507232+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/SXZ7DJHGV7M53TNEEHRKVCYD24","json":"https://pith.science/pith/SXZ7DJHGV7M53TNEEHRKVCYD24.json","graph_json":"https://pith.science/api/pith-number/SXZ7DJHGV7M53TNEEHRKVCYD24/graph.json","events_json":"https://pith.science/api/pith-number/SXZ7DJHGV7M53TNEEHRKVCYD24/events.json","paper":"https://pith.science/paper/SXZ7DJHG"},"agent_actions":{"view_html":"https://pith.science/pith/SXZ7DJHGV7M53TNEEHRKVCYD24","download_json":"https://pith.science/pith/SXZ7DJHGV7M53TNEEHRKVCYD24.json","view_paper":"https://pith.science/paper/SXZ7DJHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21615&json=true","fetch_graph":"https://pith.science/api/pith-number/SXZ7DJHGV7M53TNEEHRKVCYD24/graph.json","fetch_events":"https://pith.science/api/pith-number/SXZ7DJHGV7M53TNEEHRKVCYD24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXZ7DJHGV7M53TNEEHRKVCYD24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXZ7DJHGV7M53TNEEHRKVCYD24/action/storage_attestation","attest_author":"https://pith.science/pith/SXZ7DJHGV7M53TNEEHRKVCYD24/action/author_attestation","sign_citation":"https://pith.science/pith/SXZ7DJHGV7M53TNEEHRKVCYD24/action/citation_signature","submit_replication":"https://pith.science/pith/SXZ7DJHGV7M53TNEEHRKVCYD24/action/replication_record"}},"created_at":"2026-05-22T01:03:25.507232+00:00","updated_at":"2026-05-22T01:03:25.507232+00:00"}