{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ANJ7QSOVF5LF2DXJ7Q4PQFJHNP","short_pith_number":"pith:ANJ7QSOV","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"},"canonical_sha256":"0353f849d52f565d0ee9fc38f815276bc8245b3159405389062599f3e5d852f8","source":{"kind":"arxiv","id":"2502.10118","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10118","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10118v2","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10118","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"ANJ7QSOVF5LF","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"ANJ7QSOVF5LF2DXJ","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"ANJ7QSOV","created_at":"2026-07-05T12:04:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ANJ7QSOVF5LF2DXJ7Q4PQFJHNP","target":"record","payload":{"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"},"canonical_sha256":"0353f849d52f565d0ee9fc38f815276bc8245b3159405389062599f3e5d852f8","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"},"source_kind":"arxiv","source_id":"2502.10118","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:04:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QSdSaAp30azIfb+OKStjy8Dox9Tsdqdq3rfmbmLstwOBFVBSaGO9Jr8C1L1wwHMZnI7SEr+JJIcSs97954vEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:03:23.653362Z"},"content_sha256":"243e0fa0180ec72d80077081edd3bffa91aebd837ffae860bf60c02be1847564","schema_version":"1.0","event_id":"sha256:243e0fa0180ec72d80077081edd3bffa91aebd837ffae860bf60c02be1847564"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ANJ7QSOVF5LF2DXJ7Q4PQFJHNP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:04:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BVCoomOM41GQIlawFKj1SRP/Sftl4jHeZvAwEMTX+Eo5ZgJZL797JkHYb+4yIZh9VBZRIASibLbgKdNbAoUUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:03:23.653879Z"},"content_sha256":"3585aafc4e0253019b062bc63a430153c6a1b43b23617c772bc59b8339f69db1","schema_version":"1.0","event_id":"sha256:3585aafc4e0253019b062bc63a430153c6a1b43b23617c772bc59b8339f69db1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/bundle.json","state_url":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:03:23Z","links":{"resolver":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP","bundle":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/bundle.json","state":"https://pith.science/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ANJ7QSOVF5LF2DXJ7Q4PQFJHNP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ANJ7QSOVF5LF2DXJ7Q4PQFJHNP","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":"c150ae6079a8bb406b0501b7db57e6fa1dbec70bbfbff70e2f0e5273f74350c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:33:19Z","title_canon_sha256":"f54140e3c60a69c7d737bf5bd5033c7e6d4406c1ac259f6ae940f942b497ab8c"},"schema_version":"1.0","source":{"id":"2502.10118","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10118","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10118v2","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10118","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"ANJ7QSOVF5LF","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"ANJ7QSOVF5LF2DXJ","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"ANJ7QSOV","created_at":"2026-07-05T12:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:3585aafc4e0253019b062bc63a430153c6a1b43b23617c772bc59b8339f69db1","target":"graph","created_at":"2026-07-05T12:04:31Z","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/2502.10118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Na Min An, Sania Waheed","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:33:19Z","title":"Image Embedding Sampling Method for Diverse Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10118","kind":"arxiv","version":2},"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":"sha256:243e0fa0180ec72d80077081edd3bffa91aebd837ffae860bf60c02be1847564","target":"record","created_at":"2026-07-05T12:04:31Z","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":"c150ae6079a8bb406b0501b7db57e6fa1dbec70bbfbff70e2f0e5273f74350c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:33:19Z","title_canon_sha256":"f54140e3c60a69c7d737bf5bd5033c7e6d4406c1ac259f6ae940f942b497ab8c"},"schema_version":"1.0","source":{"id":"2502.10118","kind":"arxiv","version":2}},"canonical_sha256":"0353f849d52f565d0ee9fc38f815276bc8245b3159405389062599f3e5d852f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0353f849d52f565d0ee9fc38f815276bc8245b3159405389062599f3e5d852f8","first_computed_at":"2026-07-05T12:04:31.173559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:31.173559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e82/uHccQQC7kIeawMSX9chMDfUvy9LEWPmLmP7ttuVHlgfCnFF8J50fZqasiEk19RkuGheECNMC2hogM8phAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:31.174160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10118","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243e0fa0180ec72d80077081edd3bffa91aebd837ffae860bf60c02be1847564","sha256:3585aafc4e0253019b062bc63a430153c6a1b43b23617c772bc59b8339f69db1"],"state_sha256":"f6e7cb9df9297a59c7b81e617c6820a2032c1c9f0d1ad8ab1e661e69b2b53180"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jQI2OplYYBrzOASc/5dfmE0Alb2oPugYhcDjS/JfJ9cA/oUEMJQqyw0y/wTmcJXqDGtSsabEalz3YSaiBPshCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:03:23.657535Z","bundle_sha256":"483123c080d6edb0d7943050f906fabf63d143da93f142aded2f6c0e2a2d21da"}}