{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4C3OZ6TGZVIYHWJW5L4VE7EECA","short_pith_number":"pith:4C3OZ6TG","canonical_record":{"source":{"id":"2412.00142","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T18:55:41Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"536f4d3a601061db773f0aab46095e4cf6900153e1043c89490c4917ebc2f91d","abstract_canon_sha256":"f6176e777a3fb29464d22998ff0222c948d647c989793fd3f6c502cb749b1096"},"schema_version":"1.0"},"canonical_sha256":"e0b6ecfa66cd5183d936eaf9527c841017c4e8e83c5fb3630f445aa3b44e0c34","source":{"kind":"arxiv","id":"2412.00142","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00142","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00142v3","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00142","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"4C3OZ6TGZVIY","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"4C3OZ6TGZVIYHWJW","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"4C3OZ6TG","created_at":"2026-07-05T11:18:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4C3OZ6TGZVIYHWJW5L4VE7EECA","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00142","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T18:55:41Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"536f4d3a601061db773f0aab46095e4cf6900153e1043c89490c4917ebc2f91d","abstract_canon_sha256":"f6176e777a3fb29464d22998ff0222c948d647c989793fd3f6c502cb749b1096"},"schema_version":"1.0"},"canonical_sha256":"e0b6ecfa66cd5183d936eaf9527c841017c4e8e83c5fb3630f445aa3b44e0c34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:16.324453Z","signature_b64":"J3c5G+PrVGO96EnZXJm6Lyu+IqMbZ5Hp9JGtfkYa6hIZi1o8bkoxsrYWD4eigD1h2ueoqSyWff4pAvIV6jv4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0b6ecfa66cd5183d936eaf9527c841017c4e8e83c5fb3630f445aa3b44e0c34","last_reissued_at":"2026-07-05T11:18:16.323958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:16.323958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00142","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":"2026-07-05T11:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CgM3Pvi8ioxwVfVN+iaRohpoKlMkEMFx8Nc1fez8CW+B/uJXIAXoHjkMG86L73eUXPpXNBMRDmnLFyaCelQdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:41:28.769774Z"},"content_sha256":"e955ee4be6f2f88dd2de401e840eb0998cc01c57c9d03720b127ae560b347c45","schema_version":"1.0","event_id":"sha256:e955ee4be6f2f88dd2de401e840eb0998cc01c57c9d03720b127ae560b347c45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4C3OZ6TGZVIYHWJW5L4VE7EECA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Assaf Arbelle, Brandon Huang, Chancharik Mitra, Deva Ramanan, Leonid Karlinsky, Roei Herzig, Rogerio Feris, Tianning Chai, Trevor Darrell, Zhiqiu Lin","submitted_at":"2024-11-28T18:55:41Z","abstract_excerpt":"Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide variety of vision-language (VL) tasks. Despite strong performance, LMMs' generative outputs are not specialized for vision-language classification tasks (i.e., tasks with vision-language inputs and discrete labels) such as image classification and multiple-choice VQA. One key challenge in utilizing LMMs for these tasks is the extraction of useful features from generative LMMs. To overcome this, we propose an approach that leverages multimodal feature extraction from the LMM's latent space. Toward this end, we pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00142","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/2412.00142/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":"2026-07-05T11:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXnfz5HdtqazDfWJVeHKvnYfNHBwVh/2QKYu2xJaADhGqvfJy7Xlixodr0bcrVDLNhTZMVvKAn2cBecdvXb7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:41:28.770462Z"},"content_sha256":"5b615393c50049757490a3f584ba394c8d5ffc6c1b459149dfbf7eafdb6d052f","schema_version":"1.0","event_id":"sha256:5b615393c50049757490a3f584ba394c8d5ffc6c1b459149dfbf7eafdb6d052f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4C3OZ6TGZVIYHWJW5L4VE7EECA/bundle.json","state_url":"https://pith.science/pith/4C3OZ6TGZVIYHWJW5L4VE7EECA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4C3OZ6TGZVIYHWJW5L4VE7EECA/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":"2026-08-19T23:41:28Z","links":{"resolver":"https://pith.science/pith/4C3OZ6TGZVIYHWJW5L4VE7EECA","bundle":"https://pith.science/pith/4C3OZ6TGZVIYHWJW5L4VE7EECA/bundle.json","state":"https://pith.science/pith/4C3OZ6TGZVIYHWJW5L4VE7EECA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4C3OZ6TGZVIYHWJW5L4VE7EECA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4C3OZ6TGZVIYHWJW5L4VE7EECA","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":"f6176e777a3fb29464d22998ff0222c948d647c989793fd3f6c502cb749b1096","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T18:55:41Z","title_canon_sha256":"536f4d3a601061db773f0aab46095e4cf6900153e1043c89490c4917ebc2f91d"},"schema_version":"1.0","source":{"id":"2412.00142","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00142","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00142v3","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00142","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"4C3OZ6TGZVIY","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"4C3OZ6TGZVIYHWJW","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"4C3OZ6TG","created_at":"2026-07-05T11:18:16Z"}],"graph_snapshots":[{"event_id":"sha256:5b615393c50049757490a3f584ba394c8d5ffc6c1b459149dfbf7eafdb6d052f","target":"graph","created_at":"2026-07-05T11:18:16Z","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/2412.00142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide variety of vision-language (VL) tasks. Despite strong performance, LMMs' generative outputs are not specialized for vision-language classification tasks (i.e., tasks with vision-language inputs and discrete labels) such as image classification and multiple-choice VQA. One key challenge in utilizing LMMs for these tasks is the extraction of useful features from generative LMMs. To overcome this, we propose an approach that leverages multimodal feature extraction from the LMM's latent space. Toward this end, we pres","authors_text":"Assaf Arbelle, Brandon Huang, Chancharik Mitra, Deva Ramanan, Leonid Karlinsky, Roei Herzig, Rogerio Feris, Tianning Chai, Trevor Darrell, Zhiqiu Lin","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T18:55:41Z","title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00142","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:e955ee4be6f2f88dd2de401e840eb0998cc01c57c9d03720b127ae560b347c45","target":"record","created_at":"2026-07-05T11:18:16Z","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":"f6176e777a3fb29464d22998ff0222c948d647c989793fd3f6c502cb749b1096","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T18:55:41Z","title_canon_sha256":"536f4d3a601061db773f0aab46095e4cf6900153e1043c89490c4917ebc2f91d"},"schema_version":"1.0","source":{"id":"2412.00142","kind":"arxiv","version":3}},"canonical_sha256":"e0b6ecfa66cd5183d936eaf9527c841017c4e8e83c5fb3630f445aa3b44e0c34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0b6ecfa66cd5183d936eaf9527c841017c4e8e83c5fb3630f445aa3b44e0c34","first_computed_at":"2026-07-05T11:18:16.323958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:16.323958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J3c5G+PrVGO96EnZXJm6Lyu+IqMbZ5Hp9JGtfkYa6hIZi1o8bkoxsrYWD4eigD1h2ueoqSyWff4pAvIV6jv4DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:16.324453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00142","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e955ee4be6f2f88dd2de401e840eb0998cc01c57c9d03720b127ae560b347c45","sha256:5b615393c50049757490a3f584ba394c8d5ffc6c1b459149dfbf7eafdb6d052f"],"state_sha256":"fb664f23ed5a50fff461dfd57ed9d09079153cc469696c385985a7c8a910d9fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3lkr5XfK0tViyLJvwOqo9szc+tFbVfhLvk3g77OTPLMb7QcoWgNnGZ8LMQazG6ihrigwKzm46HRJTRQ5KhHFAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:41:28.776012Z","bundle_sha256":"8470544e5c7f80bb3325ad440b0df8502bd270e1acfe5751b664ee86f30e3cd7"}}