{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:36FNWYTQEFJMSUW5UMH4DFIRCL","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":"5d775c48c86669ceda46e2d98460240f4fc8f0c9cc8b80fde6040844ae1c27e2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-03T13:37:00Z","title_canon_sha256":"359fafc037f11a273b0be5104250dcd47d3e5e3c70828d9888d09d8d00367bfb"},"schema_version":"1.0","source":{"id":"2307.01003","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01003","created_at":"2026-07-05T07:24:51Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01003v2","created_at":"2026-07-05T07:24:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01003","created_at":"2026-07-05T07:24:51Z"},{"alias_kind":"pith_short_12","alias_value":"36FNWYTQEFJM","created_at":"2026-07-05T07:24:51Z"},{"alias_kind":"pith_short_16","alias_value":"36FNWYTQEFJMSUW5","created_at":"2026-07-05T07:24:51Z"},{"alias_kind":"pith_short_8","alias_value":"36FNWYTQ","created_at":"2026-07-05T07:24:51Z"}],"graph_snapshots":[{"event_id":"sha256:2b2baf9c63b78d513657bbc89ab814409683adba5975658b13cc904bd960aa04","target":"graph","created_at":"2026-07-05T07:24:51Z","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/2307.01003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baoyuan Wang, Delong Chen, Jianfeng Liu, Wenliang Dai","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-03T13:37:00Z","title":"Visual Instruction Tuning with Polite Flamingo"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01003","kind":"arxiv","version":2},"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:aef4816c9566f501c9e79690aff87394dad64707bc1009f1a6980284e30d0c78","target":"record","created_at":"2026-07-05T07:24:51Z","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":"5d775c48c86669ceda46e2d98460240f4fc8f0c9cc8b80fde6040844ae1c27e2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-03T13:37:00Z","title_canon_sha256":"359fafc037f11a273b0be5104250dcd47d3e5e3c70828d9888d09d8d00367bfb"},"schema_version":"1.0","source":{"id":"2307.01003","kind":"arxiv","version":2}},"canonical_sha256":"df8adb62702152c952dda30fc1951112d1b7ba34753cac232f64bbcbbf0ecc02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df8adb62702152c952dda30fc1951112d1b7ba34753cac232f64bbcbbf0ecc02","first_computed_at":"2026-07-05T07:24:51.410610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:51.410610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sgiETqNz5fUygFGSSKaBcSB+LbEHUr7GR9Dkg4vsZrnhFIRHKZc+NFNSoi3musEBdDkK9nneqb5f+uFHXP7BDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:51.411095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01003","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aef4816c9566f501c9e79690aff87394dad64707bc1009f1a6980284e30d0c78","sha256:2b2baf9c63b78d513657bbc89ab814409683adba5975658b13cc904bd960aa04"],"state_sha256":"ca23b7e9af95c331204f390b2e807035f1711d383194d81214f59d05d0d95b7e"}