{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3HMRIF7N7S5TST35XNP5RNJOKF","short_pith_number":"pith:3HMRIF7N","schema_version":"1.0","canonical_sha256":"d9d91417edfcbb394f7dbb5fd8b52e51765e4f71d8b2eeeb1f6582945df67e5e","source":{"kind":"arxiv","id":"2504.01916","version":1},"attestation_state":"computed","paper":{"title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fatima Albreiki, Kebin Wu, Mothilal Asokan","submitted_at":"2025-04-02T17:19:59Z","abstract_excerpt":"As a pioneering vision-language model, CLIP (Contrastive Language-Image Pre-training) has achieved significant success across various domains and a wide range of downstream vision-language tasks. However, the text encoders in popular CLIP models are limited to processing only 77 text tokens, which constrains their ability to effectively handle longer, detail-rich captions. Additionally, CLIP models often struggle to effectively capture detailed visual and textual information, which hampers their performance on tasks that require fine-grained analysis. To address these limitations, we present a"},"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":"2504.01916","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:19:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"44befcdd7e54851bc5f7e92de6c6ca0a1151d2dbcbcf6492645fe2ce0c6d4422","abstract_canon_sha256":"8428133dc10865abb9fe6ae30191c2c1b75a9b597b47c72823cd9f5195a98eb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:31.738429Z","signature_b64":"dlOJOTJ9nbabiOCBF6pW0BXc8Zld8IQCteb2mr2x0aOurNnntRCvvfMwV9ia2K5oODi9+h8iuDHMcZDthVfKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9d91417edfcbb394f7dbb5fd8b52e51765e4f71d8b2eeeb1f6582945df67e5e","last_reissued_at":"2026-07-05T10:43:31.737956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:31.737956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fatima Albreiki, Kebin Wu, Mothilal Asokan","submitted_at":"2025-04-02T17:19:59Z","abstract_excerpt":"As a pioneering vision-language model, CLIP (Contrastive Language-Image Pre-training) has achieved significant success across various domains and a wide range of downstream vision-language tasks. However, the text encoders in popular CLIP models are limited to processing only 77 text tokens, which constrains their ability to effectively handle longer, detail-rich captions. Additionally, CLIP models often struggle to effectively capture detailed visual and textual information, which hampers their performance on tasks that require fine-grained analysis. To address these limitations, we present a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01916","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/2504.01916/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":"2504.01916","created_at":"2026-07-05T10:43:31.738011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01916v1","created_at":"2026-07-05T10:43:31.738011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01916","created_at":"2026-07-05T10:43:31.738011+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HMRIF7N7S5T","created_at":"2026-07-05T10:43:31.738011+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HMRIF7N7S5TST35","created_at":"2026-07-05T10:43:31.738011+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HMRIF7N","created_at":"2026-07-05T10:43:31.738011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":222,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04306","citing_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","ref_index":201,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":222,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16487","citing_title":"Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF","json":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF.json","graph_json":"https://pith.science/api/pith-number/3HMRIF7N7S5TST35XNP5RNJOKF/graph.json","events_json":"https://pith.science/api/pith-number/3HMRIF7N7S5TST35XNP5RNJOKF/events.json","paper":"https://pith.science/paper/3HMRIF7N"},"agent_actions":{"view_html":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF","download_json":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF.json","view_paper":"https://pith.science/paper/3HMRIF7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01916&json=true","fetch_graph":"https://pith.science/api/pith-number/3HMRIF7N7S5TST35XNP5RNJOKF/graph.json","fetch_events":"https://pith.science/api/pith-number/3HMRIF7N7S5TST35XNP5RNJOKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/action/storage_attestation","attest_author":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/action/author_attestation","sign_citation":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/action/citation_signature","submit_replication":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/action/replication_record"}},"created_at":"2026-07-05T10:43:31.738011+00:00","updated_at":"2026-07-05T10:43:31.738011+00:00"}