{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CI3LRQZGUCJ3LGOKR2SRTINVS6","short_pith_number":"pith:CI3LRQZG","canonical_record":{"source":{"id":"2404.07204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T17:59:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"143db62e9cbabb52918ee04dff177911141a2fb06db2d3bb01d6460911fbc55b","abstract_canon_sha256":"24e6187de2699695d1f4f429cd164a0909452bd6ead6c6fc84b043717dd811ae"},"schema_version":"1.0"},"canonical_sha256":"1236b8c326a093b599ca8ea519a1b597b89b29e43c758255ac47d6d71802423a","source":{"kind":"arxiv","id":"2404.07204","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07204","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07204v1","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07204","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"CI3LRQZGUCJ3","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"CI3LRQZGUCJ3LGOK","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"CI3LRQZG","created_at":"2026-07-05T08:06:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CI3LRQZGUCJ3LGOKR2SRTINVS6","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T17:59:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"143db62e9cbabb52918ee04dff177911141a2fb06db2d3bb01d6460911fbc55b","abstract_canon_sha256":"24e6187de2699695d1f4f429cd164a0909452bd6ead6c6fc84b043717dd811ae"},"schema_version":"1.0"},"canonical_sha256":"1236b8c326a093b599ca8ea519a1b597b89b29e43c758255ac47d6d71802423a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:36.845443Z","signature_b64":"5hFCid26r8YXb3wKnz7zWbr2fAd0tT1+9JrHozKXKxRcspuYWcfXO05bjTm3z6wn0iLK4g9uv7XmQDJmEzaODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1236b8c326a093b599ca8ea519a1b597b89b29e43c758255ac47d6d71802423a","last_reissued_at":"2026-07-05T08:06:36.844919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:36.844919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07204","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":"2026-07-05T08:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yEeGNMxclR65ziczaDxfUZOsW6n3NpvYKCZsa8o9ZdNWgbpXO3E++c34gvpeDNr4uPYeIsYOFOaJSg4PipTRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:17:01.939913Z"},"content_sha256":"8da047773139e95211f7799ceaf21cbe68759e30ec7cde4d3e9449340c58dc21","schema_version":"1.0","event_id":"sha256:8da047773139e95211f7799ceaf21cbe68759e30ec7cde4d3e9449340c58dc21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CI3LRQZGUCJ3LGOKR2SRTINVS6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BRAVE: Broadening the visual encoding of vision-language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Achin Kulshrestha, Alessio Tonioni, Amir Zamir, Federico Tombari, O\\u{g}uzhan Fatih Kar, Petra Poklukar","submitted_at":"2024-04-10T17:59:45Z","abstract_excerpt":"Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several shortcomings due to the limited capabilities of vision encoders, e.g. \"blindness\" to certain image features, visual hallucination, etc. To address these issues, we study broadening the visual encoding capabilities of VLMs. We first comprehensively benchmark several vision encoders with different inductive biases for solving VLM tasks. We observe that there is no sin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07204","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/2404.07204/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":"2026-07-05T08:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JBN/Vax5RNo/akzxC7nXRcXkOBfSd6QqneXYZ/ADKfmsNF2yAgAh0kTXSmNXzzw/3eXXDRMaTZ9vMldlb+5YAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:17:01.940863Z"},"content_sha256":"bfbfd0e8c65c050987405b5e04ff3fb0748f4b827cd9cd6864ef4cafec22556c","schema_version":"1.0","event_id":"sha256:bfbfd0e8c65c050987405b5e04ff3fb0748f4b827cd9cd6864ef4cafec22556c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CI3LRQZGUCJ3LGOKR2SRTINVS6/bundle.json","state_url":"https://pith.science/pith/CI3LRQZGUCJ3LGOKR2SRTINVS6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CI3LRQZGUCJ3LGOKR2SRTINVS6/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":"2026-08-11T06:17:01Z","links":{"resolver":"https://pith.science/pith/CI3LRQZGUCJ3LGOKR2SRTINVS6","bundle":"https://pith.science/pith/CI3LRQZGUCJ3LGOKR2SRTINVS6/bundle.json","state":"https://pith.science/pith/CI3LRQZGUCJ3LGOKR2SRTINVS6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CI3LRQZGUCJ3LGOKR2SRTINVS6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CI3LRQZGUCJ3LGOKR2SRTINVS6","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":"24e6187de2699695d1f4f429cd164a0909452bd6ead6c6fc84b043717dd811ae","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T17:59:45Z","title_canon_sha256":"143db62e9cbabb52918ee04dff177911141a2fb06db2d3bb01d6460911fbc55b"},"schema_version":"1.0","source":{"id":"2404.07204","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07204","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07204v1","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07204","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"CI3LRQZGUCJ3","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"CI3LRQZGUCJ3LGOK","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"CI3LRQZG","created_at":"2026-07-05T08:06:36Z"}],"graph_snapshots":[{"event_id":"sha256:bfbfd0e8c65c050987405b5e04ff3fb0748f4b827cd9cd6864ef4cafec22556c","target":"graph","created_at":"2026-07-05T08:06:36Z","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/2404.07204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several shortcomings due to the limited capabilities of vision encoders, e.g. \"blindness\" to certain image features, visual hallucination, etc. To address these issues, we study broadening the visual encoding capabilities of VLMs. We first comprehensively benchmark several vision encoders with different inductive biases for solving VLM tasks. We observe that there is no sin","authors_text":"Achin Kulshrestha, Alessio Tonioni, Amir Zamir, Federico Tombari, O\\u{g}uzhan Fatih Kar, Petra Poklukar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T17:59:45Z","title":"BRAVE: Broadening the visual encoding of vision-language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07204","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":"sha256:8da047773139e95211f7799ceaf21cbe68759e30ec7cde4d3e9449340c58dc21","target":"record","created_at":"2026-07-05T08:06:36Z","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":"24e6187de2699695d1f4f429cd164a0909452bd6ead6c6fc84b043717dd811ae","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T17:59:45Z","title_canon_sha256":"143db62e9cbabb52918ee04dff177911141a2fb06db2d3bb01d6460911fbc55b"},"schema_version":"1.0","source":{"id":"2404.07204","kind":"arxiv","version":1}},"canonical_sha256":"1236b8c326a093b599ca8ea519a1b597b89b29e43c758255ac47d6d71802423a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1236b8c326a093b599ca8ea519a1b597b89b29e43c758255ac47d6d71802423a","first_computed_at":"2026-07-05T08:06:36.844919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:36.844919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5hFCid26r8YXb3wKnz7zWbr2fAd0tT1+9JrHozKXKxRcspuYWcfXO05bjTm3z6wn0iLK4g9uv7XmQDJmEzaODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:36.845443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07204","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8da047773139e95211f7799ceaf21cbe68759e30ec7cde4d3e9449340c58dc21","sha256:bfbfd0e8c65c050987405b5e04ff3fb0748f4b827cd9cd6864ef4cafec22556c"],"state_sha256":"bd48d6bf9d528b2b2e54cff163ea1c8d26ad87ab33561c8a1c621518f4506a37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ImTRymNfhvgyBV6rP437Vn9vPPCyyFL9vKgfCPhcbzROoKpjG33dyEAWggLKKHwmJ2dY+0QgJkXPwF1r19sFCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T06:17:01.995680Z","bundle_sha256":"68fb942cc73a93f56dba91f36addeca128dc702f30932a75273c2105856cda85"}}