{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ANJ7QSOVF5LF2DXJ7Q4PQFJHNP","short_pith_number":"pith:ANJ7QSOV","schema_version":"1.0","canonical_sha256":"0353f849d52f565d0ee9fc38f815276bc8245b3159405389062599f3e5d852f8","source":{"kind":"arxiv","id":"2502.10118","version":2},"attestation_state":"computed","paper":{"title":"Image Embedding Sampling Method for Diverse Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Na Min An, Sania Waheed","submitted_at":"2025-02-14T12:33:19Z","abstract_excerpt":"Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices and assistive technologies. Alternatively, comparably smaller VLMs prioritize high-level scene descriptions, overlooking finer details that contribute to a richer understanding of an image. In this paper, we introduce a training-free framework that enhances caption diversity and informativeness by explicitly attending to distinct image regions using a compa"},"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":"2502.10118","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:33:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f54140e3c60a69c7d737bf5bd5033c7e6d4406c1ac259f6ae940f942b497ab8c","abstract_canon_sha256":"c150ae6079a8bb406b0501b7db57e6fa1dbec70bbfbff70e2f0e5273f74350c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:31.174160Z","signature_b64":"e82/uHccQQC7kIeawMSX9chMDfUvy9LEWPmLmP7ttuVHlgfCnFF8J50fZqasiEk19RkuGheECNMC2hogM8phAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0353f849d52f565d0ee9fc38f815276bc8245b3159405389062599f3e5d852f8","last_reissued_at":"2026-07-05T12:04:31.173559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:31.173559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Embedding Sampling Method for Diverse Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Na Min An, Sania Waheed","submitted_at":"2025-02-14T12:33:19Z","abstract_excerpt":"Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices and assistive technologies. Alternatively, comparably smaller VLMs prioritize high-level scene descriptions, overlooking finer details that contribute to a richer understanding of an image. In this paper, we introduce a training-free framework that enhances caption diversity and informativeness by explicitly attending to distinct image regions using a compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10118","kind":"arxiv","version":2},"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/2502.10118/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":"2502.10118","created_at":"2026-07-05T12:04:31.173624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10118v2","created_at":"2026-07-05T12:04:31.173624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10118","created_at":"2026-07-05T12:04:31.173624+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANJ7QSOVF5LF","created_at":"2026-07-05T12:04:31.173624+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANJ7QSOVF5LF2DXJ","created_at":"2026-07-05T12:04:31.173624+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANJ7QSOV","created_at":"2026-07-05T12:04:31.173624+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/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP","json":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP.json","graph_json":"https://pith.science/api/pith-number/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/graph.json","events_json":"https://pith.science/api/pith-number/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/events.json","paper":"https://pith.science/paper/ANJ7QSOV"},"agent_actions":{"view_html":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP","download_json":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP.json","view_paper":"https://pith.science/paper/ANJ7QSOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10118&json=true","fetch_graph":"https://pith.science/api/pith-number/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/graph.json","fetch_events":"https://pith.science/api/pith-number/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/action/storage_attestation","attest_author":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/action/author_attestation","sign_citation":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/action/citation_signature","submit_replication":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/action/replication_record"}},"created_at":"2026-07-05T12:04:31.173624+00:00","updated_at":"2026-07-05T12:04:31.173624+00:00"}