{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2Z6RSOCPJ7EFOAE6OSY5M47ES6","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":"89398f108e17a5fa596fa84b74a742ee5f2fe76eff8d29e320190f5eaf72961c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-06T06:57:55Z","title_canon_sha256":"eca555a3845d3cb95fee75d0c27944c55c9199a03e31b90c3bd116e164b1c9fe"},"schema_version":"1.0","source":{"id":"2603.05964","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.05964","created_at":"2026-07-24T01:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2603.05964v3","created_at":"2026-07-24T01:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.05964","created_at":"2026-07-24T01:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"2Z6RSOCPJ7EF","created_at":"2026-07-24T01:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"2Z6RSOCPJ7EFOAE6","created_at":"2026-07-24T01:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"2Z6RSOCP","created_at":"2026-07-24T01:23:07Z"}],"graph_snapshots":[{"event_id":"sha256:957ca1975176876fcc0f059b28362dffe68c8588989ed2a24ad9de261e34ed61","target":"graph","created_at":"2026-07-24T01:23:07Z","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/2603.05964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantizing open-vocabulary object detection (OVOD) models reduces their memory and computational costs, but extremely low-bit quantization severely degrades both cross-modal (region-text) and intra-modal (region-region) alignments. This multimodal degradation is a unique challenge that prior quantization methods for closed-vocabulary detectors fail to resolve. To overcome this, we propose Quantization-Aware Training with Multimodal Alignment (QATMA), the first multimodal-aware and architecture-agnostic QAT framework tailored for OVOD. QATMA integrates two key components: (i) Curriculum QAT, wh","authors_text":"Brent Byunghoon Kang, Donghwa Kang, Hyeongboo Baek, Insoo Kim, Jibum Kim, Jinyeong Park, Seunghwan An","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-06T06:57:55Z","title":"QATMA: Quantization-Aware Training with Multimodal Alignment for Open-Vocabulary Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.05964","kind":"arxiv","version":3},"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:bd8ab9cab22779a844dbf3425d092c28753eab50bf56a6013a41eef5dfb12d11","target":"record","created_at":"2026-07-24T01:23:07Z","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":"89398f108e17a5fa596fa84b74a742ee5f2fe76eff8d29e320190f5eaf72961c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-06T06:57:55Z","title_canon_sha256":"eca555a3845d3cb95fee75d0c27944c55c9199a03e31b90c3bd116e164b1c9fe"},"schema_version":"1.0","source":{"id":"2603.05964","kind":"arxiv","version":3}},"canonical_sha256":"d67d19384f4fc857009e74b1d673e497ba0d9fd3914ce061b2bb33db8b13d50c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d67d19384f4fc857009e74b1d673e497ba0d9fd3914ce061b2bb33db8b13d50c","first_computed_at":"2026-07-24T01:23:07.011715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:23:07.011715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SWjdxJoFlM6hPIhd6/06AZlTM6TT5lY4FYWJpCJvbs83wp5p5L73EmFSyWk0Qq/4iiBh0tXzNyxwWcCUzwepBg==","signature_status":"signed_v1","signed_at":"2026-07-24T01:23:07.012786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.05964","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd8ab9cab22779a844dbf3425d092c28753eab50bf56a6013a41eef5dfb12d11","sha256:957ca1975176876fcc0f059b28362dffe68c8588989ed2a24ad9de261e34ed61"],"state_sha256":"f55e2e34747afef95ae0b05d6d75e26a5e8fd5dd64d00d41a4e462c7ea3a88a2"}