{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BLHMUKVOFCE3JEIYNLMMKYW6CO","short_pith_number":"pith:BLHMUKVO","canonical_record":{"source":{"id":"2410.09489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T10:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"50a42883f55c1e72810e54c5c2a8fabf17648614d18a63fc5de7a4b589264601","abstract_canon_sha256":"30295ba2f013197ab52d53369ecdf004e726bbdc775a868670a1f5b9c37a8d01"},"schema_version":"1.0"},"canonical_sha256":"0aceca2aae2889b491186ad8c562de13ba1f8d1813affc8576e6a8e417eb431e","source":{"kind":"arxiv","id":"2410.09489","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09489","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09489v1","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09489","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"BLHMUKVOFCE3","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"BLHMUKVOFCE3JEIY","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"BLHMUKVO","created_at":"2026-07-05T09:19:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BLHMUKVOFCE3JEIYNLMMKYW6CO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.09489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T10:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"50a42883f55c1e72810e54c5c2a8fabf17648614d18a63fc5de7a4b589264601","abstract_canon_sha256":"30295ba2f013197ab52d53369ecdf004e726bbdc775a868670a1f5b9c37a8d01"},"schema_version":"1.0"},"canonical_sha256":"0aceca2aae2889b491186ad8c562de13ba1f8d1813affc8576e6a8e417eb431e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:39.837973Z","signature_b64":"M/pX3jcsQglBKWxoSNdNeKpKxfepgJ1FUJTDA+RE20WaCttNJ7AWnSjZPpNBY2j/dxtIEpS5zWEybTP0wiKQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aceca2aae2889b491186ad8c562de13ba1f8d1813affc8576e6a8e417eb431e","last_reissued_at":"2026-07-05T09:19:39.837425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:39.837425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.09489","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":"2026-07-05T09:19:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g9i2bU92w7St9QJ872Xb+Dt1gsDnYRRse763yCQfdrsLfCS2XNt4G995X3Z8Dgn2/Oc8t+flTgM5TidRvugCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:27:07.372403Z"},"content_sha256":"2afc5a470d3f03061eeaccab80796f846b649200543a9747cfa7f77b3b4c0ea3","schema_version":"1.0","event_id":"sha256:2afc5a470d3f03061eeaccab80796f846b649200543a9747cfa7f77b3b4c0ea3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BLHMUKVOFCE3JEIYNLMMKYW6CO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Lee, Andrew Chung, Jay-Yoon Lee, Junyoung Park, Jusang Oh, Sungkyung Kim","submitted_at":"2024-10-12T10:51:05Z","abstract_excerpt":"Recent advancements in large language models have demonstrated enhanced capabilities in visual reasoning tasks by employing additional encoders for aligning different modalities. While the Q-Former has been widely used as a general encoder for aligning several modalities including image, video, audio, and 3D with large language models, previous works on its efficient training and the analysis of its individual components have been limited. In this work, we investigate the effectiveness of parameter efficient fine-tuning (PEFT) the Q-Former using InstructBLIP with visual reasoning benchmarks Sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09489","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/2410.09489/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":"2026-07-05T09:19:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xDG+1qK6UgwjmsIVhpcbMOTDdUUFIv3ZgFdANQfOeNJBckoQiRCP/0wT8azpmAUzZcZc+tdTb9Dv5NXaY0UWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:27:07.373349Z"},"content_sha256":"c2b1aa3c061c7b7d8d0e3e714b5efdedd72741f6f2b365d112a34417ebfb308b","schema_version":"1.0","event_id":"sha256:c2b1aa3c061c7b7d8d0e3e714b5efdedd72741f6f2b365d112a34417ebfb308b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BLHMUKVOFCE3JEIYNLMMKYW6CO/bundle.json","state_url":"https://pith.science/pith/BLHMUKVOFCE3JEIYNLMMKYW6CO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BLHMUKVOFCE3JEIYNLMMKYW6CO/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":"2026-08-20T04:27:07Z","links":{"resolver":"https://pith.science/pith/BLHMUKVOFCE3JEIYNLMMKYW6CO","bundle":"https://pith.science/pith/BLHMUKVOFCE3JEIYNLMMKYW6CO/bundle.json","state":"https://pith.science/pith/BLHMUKVOFCE3JEIYNLMMKYW6CO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BLHMUKVOFCE3JEIYNLMMKYW6CO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BLHMUKVOFCE3JEIYNLMMKYW6CO","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":"30295ba2f013197ab52d53369ecdf004e726bbdc775a868670a1f5b9c37a8d01","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T10:51:05Z","title_canon_sha256":"50a42883f55c1e72810e54c5c2a8fabf17648614d18a63fc5de7a4b589264601"},"schema_version":"1.0","source":{"id":"2410.09489","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09489","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09489v1","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09489","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"BLHMUKVOFCE3","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"BLHMUKVOFCE3JEIY","created_at":"2026-07-05T09:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"BLHMUKVO","created_at":"2026-07-05T09:19:39Z"}],"graph_snapshots":[{"event_id":"sha256:c2b1aa3c061c7b7d8d0e3e714b5efdedd72741f6f2b365d112a34417ebfb308b","target":"graph","created_at":"2026-07-05T09:19:39Z","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/2410.09489/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models have demonstrated enhanced capabilities in visual reasoning tasks by employing additional encoders for aligning different modalities. While the Q-Former has been widely used as a general encoder for aligning several modalities including image, video, audio, and 3D with large language models, previous works on its efficient training and the analysis of its individual components have been limited. In this work, we investigate the effectiveness of parameter efficient fine-tuning (PEFT) the Q-Former using InstructBLIP with visual reasoning benchmarks Sc","authors_text":"Adam Lee, Andrew Chung, Jay-Yoon Lee, Junyoung Park, Jusang Oh, Sungkyung Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T10:51:05Z","title":"Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09489","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":"sha256:2afc5a470d3f03061eeaccab80796f846b649200543a9747cfa7f77b3b4c0ea3","target":"record","created_at":"2026-07-05T09:19:39Z","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":"30295ba2f013197ab52d53369ecdf004e726bbdc775a868670a1f5b9c37a8d01","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T10:51:05Z","title_canon_sha256":"50a42883f55c1e72810e54c5c2a8fabf17648614d18a63fc5de7a4b589264601"},"schema_version":"1.0","source":{"id":"2410.09489","kind":"arxiv","version":1}},"canonical_sha256":"0aceca2aae2889b491186ad8c562de13ba1f8d1813affc8576e6a8e417eb431e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aceca2aae2889b491186ad8c562de13ba1f8d1813affc8576e6a8e417eb431e","first_computed_at":"2026-07-05T09:19:39.837425Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:39.837425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M/pX3jcsQglBKWxoSNdNeKpKxfepgJ1FUJTDA+RE20WaCttNJ7AWnSjZPpNBY2j/dxtIEpS5zWEybTP0wiKQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:39.837973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09489","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2afc5a470d3f03061eeaccab80796f846b649200543a9747cfa7f77b3b4c0ea3","sha256:c2b1aa3c061c7b7d8d0e3e714b5efdedd72741f6f2b365d112a34417ebfb308b"],"state_sha256":"2170e3d436d268ed118813463e7f08621c39817f33b7ce4fead8a19567e04a55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xuUxWXkSXlDhMim6xHc5as16j32WiHvymqj9BhIBFwuDdcMcq7FYuASBfu48StTWXTCSMdW7A7kwwhuHQ4r9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:27:07.380036Z","bundle_sha256":"b1ad9ecc9de6d5512f30060d60275261afc906f9203b65551b7c95250ac13123"}}