{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I5PL6S7OBO2VOCDGWKMKR4SMZD","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":"653ceba45887c0fa43e79bad33e322ee2971edb77cca478c6dac63ad59df37c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T02:11:22Z","title_canon_sha256":"831718a6ea1bf640aebba33d3b0469461cc5220eb119651ebb3d077528f0a224"},"schema_version":"1.0","source":{"id":"2506.01254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01254","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01254v1","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01254","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_12","alias_value":"I5PL6S7OBO2V","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_16","alias_value":"I5PL6S7OBO2VOCDG","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_8","alias_value":"I5PL6S7O","created_at":"2026-07-05T11:14:10Z"}],"graph_snapshots":[{"event_id":"sha256:ac9cf5d7ebb843b44a32a47b8ffd1ce36a99bee3042230c9bb153725dc837a88","target":"graph","created_at":"2026-07-05T11:14:10Z","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/2506.01254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"FastText has established itself as a fundamental algorithm for learning word representations, demonstrating exceptional capability in handling out-of-vocabulary words through character-level n-gram embeddings. However, its hash-based bucketing mechanism introduces critical limitations for large-scale industrial deployment: hash collisions cause semantic drift, and memory requirements become prohibitively expensive when dealing with real-world vocabularies containing millions of terms. This paper presents a comprehensive memory optimization framework that fundamentally reimagines FastText's mem","authors_text":"Yimin Du","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T02:11:22Z","title":"Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01254","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":"sha256:9c88f74598a6be84be410ccd6fb8a08e1d0e943cd076b4f9e03de12a9ce77e0c","target":"record","created_at":"2026-07-05T11:14:10Z","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":"653ceba45887c0fa43e79bad33e322ee2971edb77cca478c6dac63ad59df37c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T02:11:22Z","title_canon_sha256":"831718a6ea1bf640aebba33d3b0469461cc5220eb119651ebb3d077528f0a224"},"schema_version":"1.0","source":{"id":"2506.01254","kind":"arxiv","version":1}},"canonical_sha256":"475ebf4bee0bb5570866b298a8f24cc8cbec322285caae3895cbdc0560145e1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"475ebf4bee0bb5570866b298a8f24cc8cbec322285caae3895cbdc0560145e1e","first_computed_at":"2026-07-05T11:14:10.528950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:10.528950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ebk+2wozijm/hqcCDi9z4HsKsTgRjKMHKDGpOfcuLHsmPV57p4yvkLzR7mVnztcSZLxWWEo1U1X7MkZnc0CECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:10.529507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c88f74598a6be84be410ccd6fb8a08e1d0e943cd076b4f9e03de12a9ce77e0c","sha256:ac9cf5d7ebb843b44a32a47b8ffd1ce36a99bee3042230c9bb153725dc837a88"],"state_sha256":"577775322166a3069a8bf681269d0607a419307a5edf72822de644d07963befa"}