{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7JLD4KB2MW7CZRKUSNLUZYDQJD","short_pith_number":"pith:7JLD4KB2","schema_version":"1.0","canonical_sha256":"fa563e283a65be2cc55493574ce07048eeb697d537bc255ff65e6c7ce09a359d","source":{"kind":"arxiv","id":"2412.18273","version":1},"attestation_state":"computed","paper":{"title":"Sampling Bag of Views for Open-Vocabulary Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hojun Choi, Hyunjung Shim, Junsuk Choe","submitted_at":"2024-12-24T08:32:38Z","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"},"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":"2412.18273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T08:32:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"06a79cafd1ed290e58109e05df68534f506cb0522f56f8f6f0e08080225eeea7","abstract_canon_sha256":"0ac85c4934e09f59d30424a8ca2c455ad60131791ccc2bd251b46f391108708a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:53.060929Z","signature_b64":"dLo8rYzWdkXXOob4BlXIMQoUCUJZx8+/X6YMusB425+bF5xQyCsTDBZ5iIsQJC/uDy7oxIlbMRAgw38dmxZyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa563e283a65be2cc55493574ce07048eeb697d537bc255ff65e6c7ce09a359d","last_reissued_at":"2026-07-05T09:53:53.060464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:53.060464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling Bag of Views for Open-Vocabulary Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hojun Choi, Hyunjung Shim, Junsuk Choe","submitted_at":"2024-12-24T08:32:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18273","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/2412.18273/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":"2412.18273","created_at":"2026-07-05T09:53:53.060521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18273v1","created_at":"2026-07-05T09:53:53.060521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18273","created_at":"2026-07-05T09:53:53.060521+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JLD4KB2MW7C","created_at":"2026-07-05T09:53:53.060521+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JLD4KB2MW7CZRKU","created_at":"2026-07-05T09:53:53.060521+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JLD4KB2","created_at":"2026-07-05T09:53:53.060521+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/7JLD4KB2MW7CZRKUSNLUZYDQJD","json":"https://pith.science/pith/7JLD4KB2MW7CZRKUSNLUZYDQJD.json","graph_json":"https://pith.science/api/pith-number/7JLD4KB2MW7CZRKUSNLUZYDQJD/graph.json","events_json":"https://pith.science/api/pith-number/7JLD4KB2MW7CZRKUSNLUZYDQJD/events.json","paper":"https://pith.science/paper/7JLD4KB2"},"agent_actions":{"view_html":"https://pith.science/pith/7JLD4KB2MW7CZRKUSNLUZYDQJD","download_json":"https://pith.science/pith/7JLD4KB2MW7CZRKUSNLUZYDQJD.json","view_paper":"https://pith.science/paper/7JLD4KB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18273&json=true","fetch_graph":"https://pith.science/api/pith-number/7JLD4KB2MW7CZRKUSNLUZYDQJD/graph.json","fetch_events":"https://pith.science/api/pith-number/7JLD4KB2MW7CZRKUSNLUZYDQJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JLD4KB2MW7CZRKUSNLUZYDQJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JLD4KB2MW7CZRKUSNLUZYDQJD/action/storage_attestation","attest_author":"https://pith.science/pith/7JLD4KB2MW7CZRKUSNLUZYDQJD/action/author_attestation","sign_citation":"https://pith.science/pith/7JLD4KB2MW7CZRKUSNLUZYDQJD/action/citation_signature","submit_replication":"https://pith.science/pith/7JLD4KB2MW7CZRKUSNLUZYDQJD/action/replication_record"}},"created_at":"2026-07-05T09:53:53.060521+00:00","updated_at":"2026-07-05T09:53:53.060521+00:00"}