{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UDYOYHLRGNTBGI37HKTHMSRJXF","short_pith_number":"pith:UDYOYHLR","canonical_record":{"source":{"id":"2505.18115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T17:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"8ed84cd9968c46ff62d263564bc6f66934d60e74474bc8d134bc7ae26b812d75","abstract_canon_sha256":"312b420cc551ed6d0f686d5ecf0c45ce6f8c8088aefd64df3477030347706e20"},"schema_version":"1.0"},"canonical_sha256":"a0f0ec1d71336613237f3aa6764a29b95f511382b2c0f8efbefcd77bb199a137","source":{"kind":"arxiv","id":"2505.18115","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18115","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18115v1","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18115","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"UDYOYHLRGNTB","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"UDYOYHLRGNTBGI37","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"UDYOYHLR","created_at":"2026-07-05T11:08:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UDYOYHLRGNTBGI37HKTHMSRJXF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T17:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"8ed84cd9968c46ff62d263564bc6f66934d60e74474bc8d134bc7ae26b812d75","abstract_canon_sha256":"312b420cc551ed6d0f686d5ecf0c45ce6f8c8088aefd64df3477030347706e20"},"schema_version":"1.0"},"canonical_sha256":"a0f0ec1d71336613237f3aa6764a29b95f511382b2c0f8efbefcd77bb199a137","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:36.837929Z","signature_b64":"2BWrMbHQm0fUPgkiYMbQDuUU1RFVsVBqqAvICHnl5/IzYDttzHhap3/AujlakUnu9Qf0klyN3gM0okThK2w+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f0ec1d71336613237f3aa6764a29b95f511382b2c0f8efbefcd77bb199a137","last_reissued_at":"2026-07-05T11:08:36.837450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:36.837450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18115","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":"2026-07-05T11:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V1BvrZVzGbdY7sEEt1MJVyRSnm6orlZkvhdvva2kYn7JRjvSb2ILfF13KTELBMHeuQnTY2Ay04vktb1Pw3qeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:55:49.078201Z"},"content_sha256":"492c3669bc6cbdea5eabe3e7c76fe0697bae84f62d5205db9e5e4e239eddaa91","schema_version":"1.0","event_id":"sha256:492c3669bc6cbdea5eabe3e7c76fe0697bae84f62d5205db9e5e4e239eddaa91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UDYOYHLRGNTBGI37HKTHMSRJXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Ritter, Hongyin Luo, Jacob Hansen, James Glass, Junmo Kang, Leonid Karlinsky, Muhammad Jehanzeb Mirza, Rogerio Feris, Wei Lin","submitted_at":"2025-05-23T17:14:12Z","abstract_excerpt":"Visual Instruction Tuning (VisIT) data, commonly available as human-assistant conversations with images interleaved in the human turns, are currently the most widespread vehicle for aligning strong LLMs to understand visual inputs, converting them to strong LMMs. While many VisIT datasets are available, most are constructed using ad-hoc techniques developed independently by different groups. They are often poorly documented, lack reproducible code, and rely on paid, closed-source model APIs such as GPT-4, Gemini, or Claude to convert image metadata (labels) into VisIT instructions. This leads "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18115","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/2505.18115/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":"2026-07-05T11:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oNlFaxKsYxggsnrFt9895hwyjoITTesUAd+n3I56TQxbmCqzfFf4SBoBjmeUWPHTMMREQGmpZGavYv6BRLY4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:55:49.078833Z"},"content_sha256":"9bfec29daccde0a986508c3335cce10957cea217f66b1111cf802f330df9f28c","schema_version":"1.0","event_id":"sha256:9bfec29daccde0a986508c3335cce10957cea217f66b1111cf802f330df9f28c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDYOYHLRGNTBGI37HKTHMSRJXF/bundle.json","state_url":"https://pith.science/pith/UDYOYHLRGNTBGI37HKTHMSRJXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDYOYHLRGNTBGI37HKTHMSRJXF/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":"2026-08-07T17:55:49Z","links":{"resolver":"https://pith.science/pith/UDYOYHLRGNTBGI37HKTHMSRJXF","bundle":"https://pith.science/pith/UDYOYHLRGNTBGI37HKTHMSRJXF/bundle.json","state":"https://pith.science/pith/UDYOYHLRGNTBGI37HKTHMSRJXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDYOYHLRGNTBGI37HKTHMSRJXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UDYOYHLRGNTBGI37HKTHMSRJXF","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":"312b420cc551ed6d0f686d5ecf0c45ce6f8c8088aefd64df3477030347706e20","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T17:14:12Z","title_canon_sha256":"8ed84cd9968c46ff62d263564bc6f66934d60e74474bc8d134bc7ae26b812d75"},"schema_version":"1.0","source":{"id":"2505.18115","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18115","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18115v1","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18115","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"UDYOYHLRGNTB","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"UDYOYHLRGNTBGI37","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"UDYOYHLR","created_at":"2026-07-05T11:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:9bfec29daccde0a986508c3335cce10957cea217f66b1111cf802f330df9f28c","target":"graph","created_at":"2026-07-05T11:08:36Z","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/2505.18115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Instruction Tuning (VisIT) data, commonly available as human-assistant conversations with images interleaved in the human turns, are currently the most widespread vehicle for aligning strong LLMs to understand visual inputs, converting them to strong LMMs. While many VisIT datasets are available, most are constructed using ad-hoc techniques developed independently by different groups. They are often poorly documented, lack reproducible code, and rely on paid, closed-source model APIs such as GPT-4, Gemini, or Claude to convert image metadata (labels) into VisIT instructions. This leads ","authors_text":"Alan Ritter, Hongyin Luo, Jacob Hansen, James Glass, Junmo Kang, Leonid Karlinsky, Muhammad Jehanzeb Mirza, Rogerio Feris, Wei Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T17:14:12Z","title":"Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18115","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":"sha256:492c3669bc6cbdea5eabe3e7c76fe0697bae84f62d5205db9e5e4e239eddaa91","target":"record","created_at":"2026-07-05T11:08:36Z","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":"312b420cc551ed6d0f686d5ecf0c45ce6f8c8088aefd64df3477030347706e20","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T17:14:12Z","title_canon_sha256":"8ed84cd9968c46ff62d263564bc6f66934d60e74474bc8d134bc7ae26b812d75"},"schema_version":"1.0","source":{"id":"2505.18115","kind":"arxiv","version":1}},"canonical_sha256":"a0f0ec1d71336613237f3aa6764a29b95f511382b2c0f8efbefcd77bb199a137","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0f0ec1d71336613237f3aa6764a29b95f511382b2c0f8efbefcd77bb199a137","first_computed_at":"2026-07-05T11:08:36.837450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:36.837450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2BWrMbHQm0fUPgkiYMbQDuUU1RFVsVBqqAvICHnl5/IzYDttzHhap3/AujlakUnu9Qf0klyN3gM0okThK2w+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:36.837929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18115","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:492c3669bc6cbdea5eabe3e7c76fe0697bae84f62d5205db9e5e4e239eddaa91","sha256:9bfec29daccde0a986508c3335cce10957cea217f66b1111cf802f330df9f28c"],"state_sha256":"d7204c9b04a6d402ff5ee7a60710f21929885078c4e99e8d9f92900c6a0d156b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/B2S7nLxcNC96Y/M9ODW2j8cHVWpGMsITkbgJnNFIrDJH1E2MaKZ/wyQhjxQeHNFbf+052c0At17ASfnwUlECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:55:49.087103Z","bundle_sha256":"f7f0d77e202a344f04fd1139616451fc4e6302e12ae4d653031ac4ab48a07af0"}}