{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y42BSAOU3QCMA5P6LBX2QBNH6B","short_pith_number":"pith:Y42BSAOU","canonical_record":{"source":{"id":"2412.19289","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:29:38Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"921d732553a3f9e7f19c2cf5682502456817d6d5ef88fda1d29ac3bbcfb16263","abstract_canon_sha256":"e04cd4db4188cc56b5f6082083330ffea39cdcfc510646ae24b7a600ed9119cd"},"schema_version":"1.0"},"canonical_sha256":"c7341901d4dc04c075fe586fa805a7f0496ef5b9fae660c63393f30ee17947ac","source":{"kind":"arxiv","id":"2412.19289","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19289","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19289v3","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19289","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"Y42BSAOU3QCM","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"Y42BSAOU3QCMA5P6","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"Y42BSAOU","created_at":"2026-07-05T10:04:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y42BSAOU3QCMA5P6LBX2QBNH6B","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19289","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:29:38Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"921d732553a3f9e7f19c2cf5682502456817d6d5ef88fda1d29ac3bbcfb16263","abstract_canon_sha256":"e04cd4db4188cc56b5f6082083330ffea39cdcfc510646ae24b7a600ed9119cd"},"schema_version":"1.0"},"canonical_sha256":"c7341901d4dc04c075fe586fa805a7f0496ef5b9fae660c63393f30ee17947ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:59.121939Z","signature_b64":"kmVUJxtDfLcPuxtILIQqLS8FMfBH3iy8RzPa1RYH/knZ9D12bYVL2Lo5sS8PdIo0sIZTk74azC38dKKqeqxcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7341901d4dc04c075fe586fa805a7f0496ef5b9fae660c63393f30ee17947ac","last_reissued_at":"2026-07-05T10:04:59.121548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:59.121548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19289","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxIPgSX35v/HYUpe7BqqCCDZ6mvtQEbtT93gW8tEZbKu7uQgFQTOad68/E9w6r8YzYE4yUWFztnw9WVfUIOLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:26:09.424287Z"},"content_sha256":"2ccb0c0ea56fa7ba747f4d9ee1d76d5d551fa7b43c6f8760ac133230acc9c553","schema_version":"1.0","event_id":"sha256:2ccb0c0ea56fa7ba747f4d9ee1d76d5d551fa7b43c6f8760ac133230acc9c553"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y42BSAOU3QCMA5P6LBX2QBNH6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong-Jin Kim, Si-Woo Kim, Soeun Lee, Taewhan Kim","submitted_at":"2024-12-26T17:29:38Z","abstract_excerpt":"Recent lightweight image captioning models using retrieved data mainly focus on text prompts. However, previous works only utilize the retrieved text as text prompts, and the visual information relies only on the CLIP visual embedding. Because of this issue, there is a limitation that the image descriptions inherent in the prompt are not sufficiently reflected in the visual embedding space. To tackle this issue, we propose ViPCap, a novel retrieval text-based visual prompt for lightweight image captioning. ViPCap leverages the retrieved text with image information as visual prompts to enhance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19289","kind":"arxiv","version":3},"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/2412.19289/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":"2026-07-05T10:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wsgp7DN8FJpaOajjnHMsObRJ4RbHUfY0CTb0muRmdt+Ie7kyCc2P5QlgUEK+Eus6sGr4P/fUkm7KrcXjJUuqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:26:09.424856Z"},"content_sha256":"c05290aea985265628b30861fdb68acbf7c5d569575133991f773037d7eaa2e1","schema_version":"1.0","event_id":"sha256:c05290aea985265628b30861fdb68acbf7c5d569575133991f773037d7eaa2e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y42BSAOU3QCMA5P6LBX2QBNH6B/bundle.json","state_url":"https://pith.science/pith/Y42BSAOU3QCMA5P6LBX2QBNH6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y42BSAOU3QCMA5P6LBX2QBNH6B/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":"2026-08-12T13:26:09Z","links":{"resolver":"https://pith.science/pith/Y42BSAOU3QCMA5P6LBX2QBNH6B","bundle":"https://pith.science/pith/Y42BSAOU3QCMA5P6LBX2QBNH6B/bundle.json","state":"https://pith.science/pith/Y42BSAOU3QCMA5P6LBX2QBNH6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y42BSAOU3QCMA5P6LBX2QBNH6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y42BSAOU3QCMA5P6LBX2QBNH6B","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":"e04cd4db4188cc56b5f6082083330ffea39cdcfc510646ae24b7a600ed9119cd","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:29:38Z","title_canon_sha256":"921d732553a3f9e7f19c2cf5682502456817d6d5ef88fda1d29ac3bbcfb16263"},"schema_version":"1.0","source":{"id":"2412.19289","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19289","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19289v3","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19289","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"Y42BSAOU3QCM","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"Y42BSAOU3QCMA5P6","created_at":"2026-07-05T10:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"Y42BSAOU","created_at":"2026-07-05T10:04:59Z"}],"graph_snapshots":[{"event_id":"sha256:c05290aea985265628b30861fdb68acbf7c5d569575133991f773037d7eaa2e1","target":"graph","created_at":"2026-07-05T10:04:59Z","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/2412.19289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent lightweight image captioning models using retrieved data mainly focus on text prompts. However, previous works only utilize the retrieved text as text prompts, and the visual information relies only on the CLIP visual embedding. Because of this issue, there is a limitation that the image descriptions inherent in the prompt are not sufficiently reflected in the visual embedding space. To tackle this issue, we propose ViPCap, a novel retrieval text-based visual prompt for lightweight image captioning. ViPCap leverages the retrieved text with image information as visual prompts to enhance ","authors_text":"Dong-Jin Kim, Si-Woo Kim, Soeun Lee, Taewhan Kim","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:29:38Z","title":"ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19289","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":"sha256:2ccb0c0ea56fa7ba747f4d9ee1d76d5d551fa7b43c6f8760ac133230acc9c553","target":"record","created_at":"2026-07-05T10:04:59Z","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":"e04cd4db4188cc56b5f6082083330ffea39cdcfc510646ae24b7a600ed9119cd","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:29:38Z","title_canon_sha256":"921d732553a3f9e7f19c2cf5682502456817d6d5ef88fda1d29ac3bbcfb16263"},"schema_version":"1.0","source":{"id":"2412.19289","kind":"arxiv","version":3}},"canonical_sha256":"c7341901d4dc04c075fe586fa805a7f0496ef5b9fae660c63393f30ee17947ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7341901d4dc04c075fe586fa805a7f0496ef5b9fae660c63393f30ee17947ac","first_computed_at":"2026-07-05T10:04:59.121548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:59.121548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kmVUJxtDfLcPuxtILIQqLS8FMfBH3iy8RzPa1RYH/knZ9D12bYVL2Lo5sS8PdIo0sIZTk74azC38dKKqeqxcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:59.121939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19289","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ccb0c0ea56fa7ba747f4d9ee1d76d5d551fa7b43c6f8760ac133230acc9c553","sha256:c05290aea985265628b30861fdb68acbf7c5d569575133991f773037d7eaa2e1"],"state_sha256":"48fd5874f49afb959eb8c2fe12a3c4fafe05fe3a638a4d0361a5b70d9b839530"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fcoo4yT70ky2XHLLex+bNwo6OYkMg2oGNRXkRnNRnUw8RcV3t6MrO8DFPINozKDPMClL6FUsEZ06purvi7FnAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:26:09.429898Z","bundle_sha256":"a104bcf9625e00b9aa0a94707e7fa0541056c2b50cc59bdf3b32665933c32bb3"}}