{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LC5PNUVPGAR6PGEITNGFPUN2CR","short_pith_number":"pith:LC5PNUVP","canonical_record":{"source":{"id":"2410.09575","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-12T15:54:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d07816aa976a72eb0e4a47c9c61070367695bd328b400bb0dab00e0e2404c114","abstract_canon_sha256":"5a9db50d9b1e2212bc3713dbadf30d4edb697675292cb4c37270d335006890f5"},"schema_version":"1.0"},"canonical_sha256":"58baf6d2af3023e798889b4c57d1ba1475a826aee5f43e707103965f743cd554","source":{"kind":"arxiv","id":"2410.09575","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09575","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09575v2","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09575","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"pith_short_12","alias_value":"LC5PNUVPGAR6","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"pith_short_16","alias_value":"LC5PNUVPGAR6PGEI","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"pith_short_8","alias_value":"LC5PNUVP","created_at":"2026-07-05T09:55:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LC5PNUVPGAR6PGEITNGFPUN2CR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.09575","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-12T15:54:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d07816aa976a72eb0e4a47c9c61070367695bd328b400bb0dab00e0e2404c114","abstract_canon_sha256":"5a9db50d9b1e2212bc3713dbadf30d4edb697675292cb4c37270d335006890f5"},"schema_version":"1.0"},"canonical_sha256":"58baf6d2af3023e798889b4c57d1ba1475a826aee5f43e707103965f743cd554","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:35.095616Z","signature_b64":"utyKZ4bfPI9a31uLaTXFidXMgstnCegtnEN+CBXwTLrLqlD1Qz51PevJ3Pk7eOEfmbcrw8Mtfrfg2y+df4rWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58baf6d2af3023e798889b4c57d1ba1475a826aee5f43e707103965f743cd554","last_reissued_at":"2026-07-05T09:55:35.095111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:35.095111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.09575","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urnKH+pZn+5jxXuyPrPRI8KuqhUuieHcLCWPcNDKT3n9c4EWR8VhO5cyssgl3Ofjl7epPJIQ3eMiOHrGsxvjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:51:36.186799Z"},"content_sha256":"e37a6c2df3f650ac4810e7af30856eb551af8b4f692fbecc6d9c695f072ac605","schema_version":"1.0","event_id":"sha256:e37a6c2df3f650ac4810e7af30856eb551af8b4f692fbecc6d9c695f072ac605"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LC5PNUVPGAR6PGEITNGFPUN2CR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reconstructive Visual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anlin Zheng, Haochen Wang, Tiancai Wang, Xiangyu Zhang, Yucheng Zhao, Zhaoxiang Zhang, Zheng Ge","submitted_at":"2024-10-12T15:54:29Z","abstract_excerpt":"This paper introduces reconstructive visual instruction tuning (ROSS), a family of Large Multimodal Models (LMMs) that exploit vision-centric supervision signals. In contrast to conventional visual instruction tuning approaches that exclusively supervise text outputs, ROSS prompts LMMs to supervise visual outputs via reconstructing input images. By doing so, it capitalizes on the inherent richness and detail present within input images themselves, which are often lost in pure text supervision. However, producing meaningful feedback from natural images is challenging due to the heavy spatial re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09575","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/2410.09575/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":"2026-07-05T09:55:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TJrvq73ES2SOLYDRS7fuGufLCQfx/jsH6QvAqeaGtp/fYlgB+C0S2aPYCckgfkuaebXcdcsQSkT7urZ/qMDGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:51:36.187309Z"},"content_sha256":"627901555ef084266a3b95c21e2c061f2734a492975a973c375dbd705363ca55","schema_version":"1.0","event_id":"sha256:627901555ef084266a3b95c21e2c061f2734a492975a973c375dbd705363ca55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LC5PNUVPGAR6PGEITNGFPUN2CR/bundle.json","state_url":"https://pith.science/pith/LC5PNUVPGAR6PGEITNGFPUN2CR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LC5PNUVPGAR6PGEITNGFPUN2CR/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":"2026-08-11T04:51:36Z","links":{"resolver":"https://pith.science/pith/LC5PNUVPGAR6PGEITNGFPUN2CR","bundle":"https://pith.science/pith/LC5PNUVPGAR6PGEITNGFPUN2CR/bundle.json","state":"https://pith.science/pith/LC5PNUVPGAR6PGEITNGFPUN2CR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LC5PNUVPGAR6PGEITNGFPUN2CR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LC5PNUVPGAR6PGEITNGFPUN2CR","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":"5a9db50d9b1e2212bc3713dbadf30d4edb697675292cb4c37270d335006890f5","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-12T15:54:29Z","title_canon_sha256":"d07816aa976a72eb0e4a47c9c61070367695bd328b400bb0dab00e0e2404c114"},"schema_version":"1.0","source":{"id":"2410.09575","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09575","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09575v2","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09575","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"pith_short_12","alias_value":"LC5PNUVPGAR6","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"pith_short_16","alias_value":"LC5PNUVPGAR6PGEI","created_at":"2026-07-05T09:55:35Z"},{"alias_kind":"pith_short_8","alias_value":"LC5PNUVP","created_at":"2026-07-05T09:55:35Z"}],"graph_snapshots":[{"event_id":"sha256:627901555ef084266a3b95c21e2c061f2734a492975a973c375dbd705363ca55","target":"graph","created_at":"2026-07-05T09:55:35Z","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/2410.09575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces reconstructive visual instruction tuning (ROSS), a family of Large Multimodal Models (LMMs) that exploit vision-centric supervision signals. In contrast to conventional visual instruction tuning approaches that exclusively supervise text outputs, ROSS prompts LMMs to supervise visual outputs via reconstructing input images. By doing so, it capitalizes on the inherent richness and detail present within input images themselves, which are often lost in pure text supervision. However, producing meaningful feedback from natural images is challenging due to the heavy spatial re","authors_text":"Anlin Zheng, Haochen Wang, Tiancai Wang, Xiangyu Zhang, Yucheng Zhao, Zhaoxiang Zhang, Zheng Ge","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-12T15:54:29Z","title":"Reconstructive Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09575","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:e37a6c2df3f650ac4810e7af30856eb551af8b4f692fbecc6d9c695f072ac605","target":"record","created_at":"2026-07-05T09:55:35Z","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":"5a9db50d9b1e2212bc3713dbadf30d4edb697675292cb4c37270d335006890f5","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-12T15:54:29Z","title_canon_sha256":"d07816aa976a72eb0e4a47c9c61070367695bd328b400bb0dab00e0e2404c114"},"schema_version":"1.0","source":{"id":"2410.09575","kind":"arxiv","version":2}},"canonical_sha256":"58baf6d2af3023e798889b4c57d1ba1475a826aee5f43e707103965f743cd554","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58baf6d2af3023e798889b4c57d1ba1475a826aee5f43e707103965f743cd554","first_computed_at":"2026-07-05T09:55:35.095111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:35.095111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"utyKZ4bfPI9a31uLaTXFidXMgstnCegtnEN+CBXwTLrLqlD1Qz51PevJ3Pk7eOEfmbcrw8Mtfrfg2y+df4rWBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:35.095616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09575","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e37a6c2df3f650ac4810e7af30856eb551af8b4f692fbecc6d9c695f072ac605","sha256:627901555ef084266a3b95c21e2c061f2734a492975a973c375dbd705363ca55"],"state_sha256":"51b8e080acf9fc3eaa5796132ecdaf7d2ada92fd446ff32ca27bdc96c6dbb3f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOkwpsDm8u0lHaiTx3UKD3Onpu3qfeLvy6o9u25YTfP0e1NkMpAANg4/3joMJF26dEn9VKqp34LhdB5/emsPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:51:36.191139Z","bundle_sha256":"d3898920e7f702f6b08a673ccc7b13340e9f7ce5c2ac0bf523c29d19cb4a16cc"}}