{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X57NCA34DI53BMKEPCHUHAQZQV","short_pith_number":"pith:X57NCA34","canonical_record":{"source":{"id":"2412.15652","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T08:07:11Z","cross_cats_sorted":[],"title_canon_sha256":"d24ed4937fd6181c032e4533416ea484fd626b5bb366ef0242944749fd7622b6","abstract_canon_sha256":"a7535e467c13c96c45d12424c1543c54f41acd6fafc7a57fe924771d4093cb2e"},"schema_version":"1.0"},"canonical_sha256":"bf7ed1037c1a3bb0b144788f438219855a9f537a52a3b1a6dc6857221941518a","source":{"kind":"arxiv","id":"2412.15652","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15652","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15652v1","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15652","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"X57NCA34DI53","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_16","alias_value":"X57NCA34DI53BMKE","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_8","alias_value":"X57NCA34","created_at":"2026-07-05T09:52:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X57NCA34DI53BMKEPCHUHAQZQV","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15652","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T08:07:11Z","cross_cats_sorted":[],"title_canon_sha256":"d24ed4937fd6181c032e4533416ea484fd626b5bb366ef0242944749fd7622b6","abstract_canon_sha256":"a7535e467c13c96c45d12424c1543c54f41acd6fafc7a57fe924771d4093cb2e"},"schema_version":"1.0"},"canonical_sha256":"bf7ed1037c1a3bb0b144788f438219855a9f537a52a3b1a6dc6857221941518a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:27.773185Z","signature_b64":"GDx0ILMKX9nYoZcoxfjY/hgUz8YIO9EwbvbQejFlHtFQOUaVxkJcBt2Vz2bNAGYTE8Q/8KdkreX1grrv52yfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf7ed1037c1a3bb0b144788f438219855a9f537a52a3b1a6dc6857221941518a","last_reissued_at":"2026-07-05T09:52:27.772612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:27.772612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15652","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":"2026-07-05T09:52:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MDrok9c5j8lQZ8zm5cbMiK/BXjaNT2JS9pCVDYA03mmc9zkvJzNJX8mHw/jYE1g/zMWgQv5v7xODXG/GiDvWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:50:52.293683Z"},"content_sha256":"741afbde03c5a2731627fce1a3811ef7af4cb9525181ebfc4a82869eb8d35646","schema_version":"1.0","event_id":"sha256:741afbde03c5a2731627fce1a3811ef7af4cb9525181ebfc4a82869eb8d35646"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X57NCA34DI53BMKEPCHUHAQZQV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Error-driven Data-efficient Large Multimodal Model Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barry Menglong Yao (UC Davis), Lifu Huang (UC Davis), Qifan Wang (Meta AI)","submitted_at":"2024-12-20T08:07:11Z","abstract_excerpt":"Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific tuning samples are usually not readily available or expensive and time-consuming to obtain. To address this, we propose an error-driven data-efficient tuning framework that aims to efficiently adapt generic LMMs to newly emerging tasks without requiring any task-specific training samples. In our approach, a generic LMM, acting as a student model, is first evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15652","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/2412.15652/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":"2026-07-05T09:52:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Gpv7MQQqmDLVELxZIxzcfxz85LSvSzhfaycPfrnRLBDWMC58QYXpHANzZ2UkQjoDIbG+N/T2IftQhP6fr0pBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:50:52.294232Z"},"content_sha256":"bdf1709863fa4f774ce878f962aeed18a774442e0d310041945a238e5ba184df","schema_version":"1.0","event_id":"sha256:bdf1709863fa4f774ce878f962aeed18a774442e0d310041945a238e5ba184df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X57NCA34DI53BMKEPCHUHAQZQV/bundle.json","state_url":"https://pith.science/pith/X57NCA34DI53BMKEPCHUHAQZQV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X57NCA34DI53BMKEPCHUHAQZQV/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":"2026-08-11T17:50:52Z","links":{"resolver":"https://pith.science/pith/X57NCA34DI53BMKEPCHUHAQZQV","bundle":"https://pith.science/pith/X57NCA34DI53BMKEPCHUHAQZQV/bundle.json","state":"https://pith.science/pith/X57NCA34DI53BMKEPCHUHAQZQV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X57NCA34DI53BMKEPCHUHAQZQV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X57NCA34DI53BMKEPCHUHAQZQV","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":"a7535e467c13c96c45d12424c1543c54f41acd6fafc7a57fe924771d4093cb2e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T08:07:11Z","title_canon_sha256":"d24ed4937fd6181c032e4533416ea484fd626b5bb366ef0242944749fd7622b6"},"schema_version":"1.0","source":{"id":"2412.15652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15652","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15652v1","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15652","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"X57NCA34DI53","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_16","alias_value":"X57NCA34DI53BMKE","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_8","alias_value":"X57NCA34","created_at":"2026-07-05T09:52:27Z"}],"graph_snapshots":[{"event_id":"sha256:bdf1709863fa4f774ce878f962aeed18a774442e0d310041945a238e5ba184df","target":"graph","created_at":"2026-07-05T09:52:27Z","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/2412.15652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific tuning samples are usually not readily available or expensive and time-consuming to obtain. To address this, we propose an error-driven data-efficient tuning framework that aims to efficiently adapt generic LMMs to newly emerging tasks without requiring any task-specific training samples. In our approach, a generic LMM, acting as a student model, is first evaluat","authors_text":"Barry Menglong Yao (UC Davis), Lifu Huang (UC Davis), Qifan Wang (Meta AI)","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T08:07:11Z","title":"Error-driven Data-efficient Large Multimodal Model Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15652","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":"sha256:741afbde03c5a2731627fce1a3811ef7af4cb9525181ebfc4a82869eb8d35646","target":"record","created_at":"2026-07-05T09:52:27Z","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":"a7535e467c13c96c45d12424c1543c54f41acd6fafc7a57fe924771d4093cb2e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T08:07:11Z","title_canon_sha256":"d24ed4937fd6181c032e4533416ea484fd626b5bb366ef0242944749fd7622b6"},"schema_version":"1.0","source":{"id":"2412.15652","kind":"arxiv","version":1}},"canonical_sha256":"bf7ed1037c1a3bb0b144788f438219855a9f537a52a3b1a6dc6857221941518a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf7ed1037c1a3bb0b144788f438219855a9f537a52a3b1a6dc6857221941518a","first_computed_at":"2026-07-05T09:52:27.772612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:27.772612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GDx0ILMKX9nYoZcoxfjY/hgUz8YIO9EwbvbQejFlHtFQOUaVxkJcBt2Vz2bNAGYTE8Q/8KdkreX1grrv52yfAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:27.773185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:741afbde03c5a2731627fce1a3811ef7af4cb9525181ebfc4a82869eb8d35646","sha256:bdf1709863fa4f774ce878f962aeed18a774442e0d310041945a238e5ba184df"],"state_sha256":"552c3e24721ae120b95a843ce7828d78ee4733c871357591b8468bd311d6681b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l28gzPT/8PdkZuD/YgZvBmeVeScnGRRt+bHGM7JkTrihHZOQBtuZ3luzxoAiVkLgX2oanHEYqURswn4mZL+6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:50:52.300993Z","bundle_sha256":"cc5da7afee371d88506f3e502223d58208aa9807b86b97866f49a7ad9d0f2065"}}