{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:36FNWYTQEFJMSUW5UMH4DFIRCL","short_pith_number":"pith:36FNWYTQ","schema_version":"1.0","canonical_sha256":"df8adb62702152c952dda30fc1951112d1b7ba34753cac232f64bbcbbf0ecc02","source":{"kind":"arxiv","id":"2307.01003","version":2},"attestation_state":"computed","paper":{"title":"Visual Instruction Tuning with Polite Flamingo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baoyuan Wang, Delong Chen, Jianfeng Liu, Wenliang Dai","submitted_at":"2023-07-03T13:37:00Z","abstract_excerpt":"Recent research has demonstrated that the multi-task fine-tuning of multi-modal Large Language Models (LLMs) using an assortment of annotated downstream vision-language datasets significantly enhances their performance. Yet, during this process, a side effect, which we termed as the \"multi-modal alignment tax\", surfaces. This side effect negatively impacts the model's ability to format responses appropriately -- for instance, its \"politeness\" -- due to the overly succinct and unformatted nature of raw annotations, resulting in reduced human preference. In this paper, we introduce Polite Flamin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.01003","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-03T13:37:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"359fafc037f11a273b0be5104250dcd47d3e5e3c70828d9888d09d8d00367bfb","abstract_canon_sha256":"5d775c48c86669ceda46e2d98460240f4fc8f0c9cc8b80fde6040844ae1c27e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:51.411095Z","signature_b64":"sgiETqNz5fUygFGSSKaBcSB+LbEHUr7GR9Dkg4vsZrnhFIRHKZc+NFNSoi3musEBdDkK9nneqb5f+uFHXP7BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df8adb62702152c952dda30fc1951112d1b7ba34753cac232f64bbcbbf0ecc02","last_reissued_at":"2026-07-05T07:24:51.410610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:51.410610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Instruction Tuning with Polite Flamingo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baoyuan Wang, Delong Chen, Jianfeng Liu, Wenliang Dai","submitted_at":"2023-07-03T13:37:00Z","abstract_excerpt":"Recent research has demonstrated that the multi-task fine-tuning of multi-modal Large Language Models (LLMs) using an assortment of annotated downstream vision-language datasets significantly enhances their performance. Yet, during this process, a side effect, which we termed as the \"multi-modal alignment tax\", surfaces. This side effect negatively impacts the model's ability to format responses appropriately -- for instance, its \"politeness\" -- due to the overly succinct and unformatted nature of raw annotations, resulting in reduced human preference. In this paper, we introduce Polite Flamin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01003","kind":"arxiv","version":2},"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/2307.01003/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.01003","created_at":"2026-07-05T07:24:51.410668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01003v2","created_at":"2026-07-05T07:24:51.410668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01003","created_at":"2026-07-05T07:24:51.410668+00:00"},{"alias_kind":"pith_short_12","alias_value":"36FNWYTQEFJM","created_at":"2026-07-05T07:24:51.410668+00:00"},{"alias_kind":"pith_short_16","alias_value":"36FNWYTQEFJMSUW5","created_at":"2026-07-05T07:24:51.410668+00:00"},{"alias_kind":"pith_short_8","alias_value":"36FNWYTQ","created_at":"2026-07-05T07:24:51.410668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.03744","citing_title":"Improved Baselines with Visual Instruction Tuning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL","json":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL.json","graph_json":"https://pith.science/api/pith-number/36FNWYTQEFJMSUW5UMH4DFIRCL/graph.json","events_json":"https://pith.science/api/pith-number/36FNWYTQEFJMSUW5UMH4DFIRCL/events.json","paper":"https://pith.science/paper/36FNWYTQ"},"agent_actions":{"view_html":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL","download_json":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL.json","view_paper":"https://pith.science/paper/36FNWYTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01003&json=true","fetch_graph":"https://pith.science/api/pith-number/36FNWYTQEFJMSUW5UMH4DFIRCL/graph.json","fetch_events":"https://pith.science/api/pith-number/36FNWYTQEFJMSUW5UMH4DFIRCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL/action/storage_attestation","attest_author":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL/action/author_attestation","sign_citation":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL/action/citation_signature","submit_replication":"https://pith.science/pith/36FNWYTQEFJMSUW5UMH4DFIRCL/action/replication_record"}},"created_at":"2026-07-05T07:24:51.410668+00:00","updated_at":"2026-07-05T07:24:51.410668+00:00"}