{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:45344GNCX5D3JSA2RSIAXF7XKC","short_pith_number":"pith:45344GNC","canonical_record":{"source":{"id":"2608.05260","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:09:24Z","cross_cats_sorted":[],"title_canon_sha256":"6b84e25eddd836ec4e661f3c76b6639ae80b4f275c45108863e905a3e124f2d4","abstract_canon_sha256":"61a031d1f8fe773c206ac2cf3654d0702ff256dd90fe2b3b359832f88e2f5ae9"},"schema_version":"1.0"},"canonical_sha256":"e777ce19a2bf47b4c81a8c900b97f750bace5ed71dede2a805d6108bab0b453e","source":{"kind":"arxiv","id":"2608.05260","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05260","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05260v1","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05260","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_12","alias_value":"45344GNCX5D3","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_16","alias_value":"45344GNCX5D3JSA2","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_8","alias_value":"45344GNC","created_at":"2026-08-07T00:46:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:45344GNCX5D3JSA2RSIAXF7XKC","target":"record","payload":{"canonical_record":{"source":{"id":"2608.05260","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:09:24Z","cross_cats_sorted":[],"title_canon_sha256":"6b84e25eddd836ec4e661f3c76b6639ae80b4f275c45108863e905a3e124f2d4","abstract_canon_sha256":"61a031d1f8fe773c206ac2cf3654d0702ff256dd90fe2b3b359832f88e2f5ae9"},"schema_version":"1.0"},"canonical_sha256":"e777ce19a2bf47b4c81a8c900b97f750bace5ed71dede2a805d6108bab0b453e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:46:37.860718Z","signature_b64":"8+HHLfn3BmWmLj7cm5u1ABBjO6aK4VjyORH5gUFjUC7iypa8+kAKwjwy5C2wm8IWUMBkwYnL40g/QSkFHRWHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e777ce19a2bf47b4c81a8c900b97f750bace5ed71dede2a805d6108bab0b453e","last_reissued_at":"2026-08-07T00:46:37.859325Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:46:37.859325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.05260","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-07T00:46:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VQw1nod89nZFCrKvcjjN221gkSYlRj4yNoOfXqeGMer2e39NVRqKTGLk3Ee2KkaR68waf8Vbl5u1hseVAiPfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:09:02.322280Z"},"content_sha256":"e8429a27d2431c13cfded9ed5dfbb9ccbb07b4188778665d52047d0d68e4532c","schema_version":"1.0","event_id":"sha256:e8429a27d2431c13cfded9ed5dfbb9ccbb07b4188778665d52047d0d68e4532c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:45344GNCX5D3JSA2RSIAXF7XKC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Paragraph is Worth a Thousand Captions: Rethinking Text Supervision for Vision-Language Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amin Tabrizian, Arsyi Aziz, Binshuai Wang, Mahyar Ghazanfari, Peng Wei","submitted_at":"2026-08-05T17:09:24Z","abstract_excerpt":"Contrastive vision-language models such as CLIP and BLIP are typically trained on short image captions, limiting their ability to retrieve images from detailed textual descriptions. While methods such as Long-CLIP extend the token limit through positional embedding interpolation, we ask a simpler question: does training text granularity alone determine long-text retrieval performance? We present a systematic study of supervision ranging from single captions to multi-sentence paragraphs for contrastive image-text retrieval. Using a synthetic pipeline based on Qwen2-VL and Llama 3.2 Vision, we g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05260","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/2608.05260/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":"2026-08-07T00:46:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iU4wRWNQe1IKIpXHRXCRFV/g57wP4bzu5+iv+0UmG3Q7066miLcqjcVyN6pSxtTyaEyhi3NIkCrBhhgttUY3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:09:02.322799Z"},"content_sha256":"a6575e692b8eef5817910b38bc19a56fb3c7226872c2eb8e8782d617cb8942ca","schema_version":"1.0","event_id":"sha256:a6575e692b8eef5817910b38bc19a56fb3c7226872c2eb8e8782d617cb8942ca"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:45344GNCX5D3JSA2RSIAXF7XKC","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2024.alvr-1.9) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Rösch, P.J., Oswald, N., Geierhos, M., Libovický, J.: Enhancing conceptual un- derstanding in multimodal contrastive learning through hard negative samples. In: Proceedings of the 3rd Workshop on Advances in Language and Vision Research (AL","arxiv_id":"2608.05260","detector":"doi_compliance","evidence":{"ref_index":17,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2024.alvr-","reconstructed_doi":"10.18653/v1/2024.alvr-1.9"},"severity":"advisory","ref_index":17,"audited_at":"2026-08-08T17:08:07.382076Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2024.alvr-1.9","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"4cc8eb9ed9104053affe7c311dba4bb1e82676eeba14cadee47d76ba34dbcc78","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18695,"payload_sha256":"e290f2c344d81b7efce94e59292ae57a196a7943c0366fdcfa996ecb7112d882","signature_b64":"eZ8pyW6IWVstpydalD8VOFCc0WCrBYkeRn/hQEgx1RQNnZhp7LWBcn5n93PurE1MvIMcEY+/1KlIs4EZ7oxUBw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-08T17:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CBbRhS6zam0SADT225QgLrfvTnyHZkZ3K5eW2TLQ+Go5ycawaxJU+xv6nBmga+jjUPdTkSPGyyrxQ48v9POLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:09:02.326400Z"},"content_sha256":"887c8ae11a63b08776668f3fc80cbd99e4e0ba811cd9b52f447d336e7c2b3ce4","schema_version":"1.0","event_id":"sha256:887c8ae11a63b08776668f3fc80cbd99e4e0ba811cd9b52f447d336e7c2b3ce4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/45344GNCX5D3JSA2RSIAXF7XKC/bundle.json","state_url":"https://pith.science/pith/45344GNCX5D3JSA2RSIAXF7XKC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/45344GNCX5D3JSA2RSIAXF7XKC/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":"2026-08-23T19:09:02Z","links":{"resolver":"https://pith.science/pith/45344GNCX5D3JSA2RSIAXF7XKC","bundle":"https://pith.science/pith/45344GNCX5D3JSA2RSIAXF7XKC/bundle.json","state":"https://pith.science/pith/45344GNCX5D3JSA2RSIAXF7XKC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/45344GNCX5D3JSA2RSIAXF7XKC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:45344GNCX5D3JSA2RSIAXF7XKC","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"61a031d1f8fe773c206ac2cf3654d0702ff256dd90fe2b3b359832f88e2f5ae9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:09:24Z","title_canon_sha256":"6b84e25eddd836ec4e661f3c76b6639ae80b4f275c45108863e905a3e124f2d4"},"schema_version":"1.0","source":{"id":"2608.05260","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05260","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05260v1","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05260","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_12","alias_value":"45344GNCX5D3","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_16","alias_value":"45344GNCX5D3JSA2","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_8","alias_value":"45344GNC","created_at":"2026-08-07T00:46:37Z"}],"graph_snapshots":[{"event_id":"sha256:a6575e692b8eef5817910b38bc19a56fb3c7226872c2eb8e8782d617cb8942ca","target":"graph","created_at":"2026-08-07T00:46:37Z","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/2608.05260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive vision-language models such as CLIP and BLIP are typically trained on short image captions, limiting their ability to retrieve images from detailed textual descriptions. While methods such as Long-CLIP extend the token limit through positional embedding interpolation, we ask a simpler question: does training text granularity alone determine long-text retrieval performance? We present a systematic study of supervision ranging from single captions to multi-sentence paragraphs for contrastive image-text retrieval. Using a synthetic pipeline based on Qwen2-VL and Llama 3.2 Vision, we g","authors_text":"Amin Tabrizian, Arsyi Aziz, Binshuai Wang, Mahyar Ghazanfari, Peng Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:09:24Z","title":"A Paragraph is Worth a Thousand Captions: Rethinking Text Supervision for Vision-Language Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05260","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:e8429a27d2431c13cfded9ed5dfbb9ccbb07b4188778665d52047d0d68e4532c","target":"record","created_at":"2026-08-07T00:46:37Z","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":"61a031d1f8fe773c206ac2cf3654d0702ff256dd90fe2b3b359832f88e2f5ae9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:09:24Z","title_canon_sha256":"6b84e25eddd836ec4e661f3c76b6639ae80b4f275c45108863e905a3e124f2d4"},"schema_version":"1.0","source":{"id":"2608.05260","kind":"arxiv","version":1}},"canonical_sha256":"e777ce19a2bf47b4c81a8c900b97f750bace5ed71dede2a805d6108bab0b453e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e777ce19a2bf47b4c81a8c900b97f750bace5ed71dede2a805d6108bab0b453e","first_computed_at":"2026-08-07T00:46:37.859325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:46:37.859325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+HHLfn3BmWmLj7cm5u1ABBjO6aK4VjyORH5gUFjUC7iypa8+kAKwjwy5C2wm8IWUMBkwYnL40g/QSkFHRWHCQ==","signature_status":"signed_v1","signed_at":"2026-08-07T00:46:37.860718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05260","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8429a27d2431c13cfded9ed5dfbb9ccbb07b4188778665d52047d0d68e4532c","sha256:a6575e692b8eef5817910b38bc19a56fb3c7226872c2eb8e8782d617cb8942ca","sha256:887c8ae11a63b08776668f3fc80cbd99e4e0ba811cd9b52f447d336e7c2b3ce4"],"state_sha256":"7f518d75048eb64bb05a27a0a88d99d973d87420c23cf2313778a32e0772266b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"awKS8PUAn7bc3YJj0Wd9U7ix2kodP4uJ+AIhrvRwSFbUhDGxgRLmSxI7ayxjuFNjemwCvQLhK2cU8tbV9T3uCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T19:09:02.328497Z","bundle_sha256":"ea56a8855c56888f79593d3a5af17ac59d38c65f1e5765a02a979d35a5ff928e"}}