{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3HMRIF7N7S5TST35XNP5RNJOKF","short_pith_number":"pith:3HMRIF7N","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"},"canonical_sha256":"d9d91417edfcbb394f7dbb5fd8b52e51765e4f71d8b2eeeb1f6582945df67e5e","source":{"kind":"arxiv","id":"2504.01916","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01916","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01916v1","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01916","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"3HMRIF7N7S5T","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_16","alias_value":"3HMRIF7N7S5TST35","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_8","alias_value":"3HMRIF7N","created_at":"2026-07-05T10:43:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3HMRIF7N7S5TST35XNP5RNJOKF","target":"record","payload":{"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"},"canonical_sha256":"d9d91417edfcbb394f7dbb5fd8b52e51765e4f71d8b2eeeb1f6582945df67e5e","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"},"source_kind":"arxiv","source_id":"2504.01916","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":"2026-07-05T10:43:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Phosk5o0sUJOW7DSBMVOM0K4g/J3rJVEM3x4a+MszpiJNRs0p9fP7X59j/Wd8AVIfpaTHwEu0ZiKl0vAFhzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:20:24.110412Z"},"content_sha256":"349e6cbfa45c7269360bdb90ab7ba2a4ee6a4592682ab54b238c1d341573643c","schema_version":"1.0","event_id":"sha256:349e6cbfa45c7269360bdb90ab7ba2a4ee6a4592682ab54b238c1d341573643c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3HMRIF7N7S5TST35XNP5RNJOKF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7MWeb2uK8UShMbxm1+mAHf3e7KebK4OgIfzFPqtgloF3p5b+q1R+NPti5rZxUL7cs2cUV2fV4zky7JAieVqvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:20:24.110910Z"},"content_sha256":"e66153962bd8fe66dfa3f2a9e9d05213aca1414b64b7b40da9bca4b1a483650d","schema_version":"1.0","event_id":"sha256:e66153962bd8fe66dfa3f2a9e9d05213aca1414b64b7b40da9bca4b1a483650d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/bundle.json","state_url":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HMRIF7N7S5TST35XNP5RNJOKF/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":"2026-08-09T03:20:24Z","links":{"resolver":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF","bundle":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/bundle.json","state":"https://pith.science/pith/3HMRIF7N7S5TST35XNP5RNJOKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HMRIF7N7S5TST35XNP5RNJOKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3HMRIF7N7S5TST35XNP5RNJOKF","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":"8428133dc10865abb9fe6ae30191c2c1b75a9b597b47c72823cd9f5195a98eb7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:19:59Z","title_canon_sha256":"44befcdd7e54851bc5f7e92de6c6ca0a1151d2dbcbcf6492645fe2ce0c6d4422"},"schema_version":"1.0","source":{"id":"2504.01916","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01916","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01916v1","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01916","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"3HMRIF7N7S5T","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_16","alias_value":"3HMRIF7N7S5TST35","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_8","alias_value":"3HMRIF7N","created_at":"2026-07-05T10:43:31Z"}],"graph_snapshots":[{"event_id":"sha256:e66153962bd8fe66dfa3f2a9e9d05213aca1414b64b7b40da9bca4b1a483650d","target":"graph","created_at":"2026-07-05T10:43:31Z","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/2504.01916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fatima Albreiki, Kebin Wu, Mothilal Asokan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:19:59Z","title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01916","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":"sha256:349e6cbfa45c7269360bdb90ab7ba2a4ee6a4592682ab54b238c1d341573643c","target":"record","created_at":"2026-07-05T10:43:31Z","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":"8428133dc10865abb9fe6ae30191c2c1b75a9b597b47c72823cd9f5195a98eb7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:19:59Z","title_canon_sha256":"44befcdd7e54851bc5f7e92de6c6ca0a1151d2dbcbcf6492645fe2ce0c6d4422"},"schema_version":"1.0","source":{"id":"2504.01916","kind":"arxiv","version":1}},"canonical_sha256":"d9d91417edfcbb394f7dbb5fd8b52e51765e4f71d8b2eeeb1f6582945df67e5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9d91417edfcbb394f7dbb5fd8b52e51765e4f71d8b2eeeb1f6582945df67e5e","first_computed_at":"2026-07-05T10:43:31.737956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:31.737956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dlOJOTJ9nbabiOCBF6pW0BXc8Zld8IQCteb2mr2x0aOurNnntRCvvfMwV9ia2K5oODi9+h8iuDHMcZDthVfKAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:31.738429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01916","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:349e6cbfa45c7269360bdb90ab7ba2a4ee6a4592682ab54b238c1d341573643c","sha256:e66153962bd8fe66dfa3f2a9e9d05213aca1414b64b7b40da9bca4b1a483650d"],"state_sha256":"14c0ad236181963e697974492d18e1d5ac95e28805640677854d2bee44d24a0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p8M6pR7yN2FjVfi4pfVh9BcdjFGHDiL6NGnyHTkjCW+hUurfvrEtPzCfUZTUpXMSCONO+e3q/FGquIc7S0P5AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:20:24.116129Z","bundle_sha256":"1e74253ff086334bc1a0b733621ea110f1618164dade1a6554412f5fdff6112a"}}