{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7JLD4KB2MW7CZRKUSNLUZYDQJD","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":"0ac85c4934e09f59d30424a8ca2c455ad60131791ccc2bd251b46f391108708a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T08:32:38Z","title_canon_sha256":"06a79cafd1ed290e58109e05df68534f506cb0522f56f8f6f0e08080225eeea7"},"schema_version":"1.0","source":{"id":"2412.18273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18273","created_at":"2026-07-05T09:53:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18273v1","created_at":"2026-07-05T09:53:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18273","created_at":"2026-07-05T09:53:53Z"},{"alias_kind":"pith_short_12","alias_value":"7JLD4KB2MW7C","created_at":"2026-07-05T09:53:53Z"},{"alias_kind":"pith_short_16","alias_value":"7JLD4KB2MW7CZRKU","created_at":"2026-07-05T09:53:53Z"},{"alias_kind":"pith_short_8","alias_value":"7JLD4KB2","created_at":"2026-07-05T09:53:53Z"}],"graph_snapshots":[{"event_id":"sha256:5572174fdf097f6ceb95222b656ad74c7e18cfe5412be6b5911b4268b723425e","target":"graph","created_at":"2026-07-05T09:53:53Z","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/2412.18273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing open-vocabulary object detection (OVD) develops methods for testing unseen categories by aligning object region embeddings with corresponding VLM features. A recent study leverages the idea that VLMs implicitly learn compositional structures of semantic concepts within the image. Instead of using an individual region embedding, it utilizes a bag of region embeddings as a new representation to incorporate compositional structures into the OVD task. However, this approach often fails to capture the contextual concepts of each region, leading to noisy compositional structures. This resul","authors_text":"Hojun Choi, Hyunjung Shim, Junsuk Choe","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T08:32:38Z","title":"Sampling Bag of Views for Open-Vocabulary Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18273","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":"sha256:2999a6b3564728f4cbf09971e0a1636c30d32938279a665c35006cd4661ed2c9","target":"record","created_at":"2026-07-05T09:53:53Z","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":"0ac85c4934e09f59d30424a8ca2c455ad60131791ccc2bd251b46f391108708a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T08:32:38Z","title_canon_sha256":"06a79cafd1ed290e58109e05df68534f506cb0522f56f8f6f0e08080225eeea7"},"schema_version":"1.0","source":{"id":"2412.18273","kind":"arxiv","version":1}},"canonical_sha256":"fa563e283a65be2cc55493574ce07048eeb697d537bc255ff65e6c7ce09a359d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa563e283a65be2cc55493574ce07048eeb697d537bc255ff65e6c7ce09a359d","first_computed_at":"2026-07-05T09:53:53.060464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:53.060464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dLo8rYzWdkXXOob4BlXIMQoUCUJZx8+/X6YMusB425+bF5xQyCsTDBZ5iIsQJC/uDy7oxIlbMRAgw38dmxZyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:53.060929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2999a6b3564728f4cbf09971e0a1636c30d32938279a665c35006cd4661ed2c9","sha256:5572174fdf097f6ceb95222b656ad74c7e18cfe5412be6b5911b4268b723425e"],"state_sha256":"efa027a349fbfe4c75dcab023950962bb81df4939b0c920ecd8b501136ff3264"}