{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4OQYBTMWJYRZCIDX7TTD3PADTY","short_pith_number":"pith:4OQYBTMW","canonical_record":{"source":{"id":"2606.19944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T08:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"ed7d2168fcb676b2b120f26ad63a21511db69327dcca17eec7577e3caeb5e600","abstract_canon_sha256":"022233364cd599373be0d27e38e952de8a71485193ba65acd01b81262b8edcc2"},"schema_version":"1.0"},"canonical_sha256":"e3a180cd964e23912077fce63dbc039e2e6ea6c1bc6ada85facc2c6a0491c2db","source":{"kind":"arxiv","id":"2606.19944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19944","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19944v1","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19944","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"4OQYBTMWJYRZ","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"4OQYBTMWJYRZCIDX","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"4OQYBTMW","created_at":"2026-06-19T16:12:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4OQYBTMWJYRZCIDX7TTD3PADTY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T08:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"ed7d2168fcb676b2b120f26ad63a21511db69327dcca17eec7577e3caeb5e600","abstract_canon_sha256":"022233364cd599373be0d27e38e952de8a71485193ba65acd01b81262b8edcc2"},"schema_version":"1.0"},"canonical_sha256":"e3a180cd964e23912077fce63dbc039e2e6ea6c1bc6ada85facc2c6a0491c2db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:58.863085Z","signature_b64":"ZKisFihZRxtZqz6FQnoXaeBozZ/qQz3a/lnl+Of4cMX/6/fNsdqAXI9fJ2u0FVgvcNBG+cr2x7RGJzUcqQZXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3a180cd964e23912077fce63dbc039e2e6ea6c1bc6ada85facc2c6a0491c2db","last_reissued_at":"2026-06-19T16:12:58.862677Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:58.862677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19944","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":"2026-06-19T16:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QJOc2o1Q9eZWVyd7489ea6vgU7kKO4uZLM/d9qM8SnkgUzXurPl6Ou4eVo8IgFcfEWrmVQNJVHoXL81BTf5iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T09:07:34.509078Z"},"content_sha256":"0ade51ea9fb4d90494c6f03d9a48a89677f1c04dc4290b9d6d3d55c753465613","schema_version":"1.0","event_id":"sha256:0ade51ea9fb4d90494c6f03d9a48a89677f1c04dc4290b9d6d3d55c753465613"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4OQYBTMWJYRZCIDX7TTD3PADTY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyi Lin, Guanhua Chen, Huimin Huang, Ruiluo Wu, Ruize Han, Wang Song, Xian Wu, Yifeng Wu","submitted_at":"2026-06-18T08:40:41Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) often lose track of the right image regions during fine-grained spatial reasoning, because a textual query rarely carries any explicit geometric anchor into the pixel domain. Prevailing remedies either rewire the model's weights or pad the prompt with verbose instructions, yet neither reliably pins the language to the correct visual coordinates without eroding the backbone's general competence. We introduce Timage, a paradigm that recasts multimodal understanding as an alignment problem solved at the input: the query is drawn, as a typeset overlay, onto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19944","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/2606.19944/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":"2026-06-19T16:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+bFP6I0q1qHNmpzuUylcCy3pMc9+VSxBibyB4zoRKR9O0tmS2v0F24sRcNGWFKymX+rP2eocNp62Di2h6bFBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T09:07:34.509483Z"},"content_sha256":"7193f19309cc4508c027f19db8b4ad6372d0caec7b1dac6679514a6aeff8b8d6","schema_version":"1.0","event_id":"sha256:7193f19309cc4508c027f19db8b4ad6372d0caec7b1dac6679514a6aeff8b8d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OQYBTMWJYRZCIDX7TTD3PADTY/bundle.json","state_url":"https://pith.science/pith/4OQYBTMWJYRZCIDX7TTD3PADTY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OQYBTMWJYRZCIDX7TTD3PADTY/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":"2026-07-04T09:07:34Z","links":{"resolver":"https://pith.science/pith/4OQYBTMWJYRZCIDX7TTD3PADTY","bundle":"https://pith.science/pith/4OQYBTMWJYRZCIDX7TTD3PADTY/bundle.json","state":"https://pith.science/pith/4OQYBTMWJYRZCIDX7TTD3PADTY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OQYBTMWJYRZCIDX7TTD3PADTY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4OQYBTMWJYRZCIDX7TTD3PADTY","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":"022233364cd599373be0d27e38e952de8a71485193ba65acd01b81262b8edcc2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T08:40:41Z","title_canon_sha256":"ed7d2168fcb676b2b120f26ad63a21511db69327dcca17eec7577e3caeb5e600"},"schema_version":"1.0","source":{"id":"2606.19944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19944","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19944v1","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19944","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"4OQYBTMWJYRZ","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"4OQYBTMWJYRZCIDX","created_at":"2026-06-19T16:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"4OQYBTMW","created_at":"2026-06-19T16:12:58Z"}],"graph_snapshots":[{"event_id":"sha256:7193f19309cc4508c027f19db8b4ad6372d0caec7b1dac6679514a6aeff8b8d6","target":"graph","created_at":"2026-06-19T16:12:58Z","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/2606.19944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) often lose track of the right image regions during fine-grained spatial reasoning, because a textual query rarely carries any explicit geometric anchor into the pixel domain. Prevailing remedies either rewire the model's weights or pad the prompt with verbose instructions, yet neither reliably pins the language to the correct visual coordinates without eroding the backbone's general competence. We introduce Timage, a paradigm that recasts multimodal understanding as an alignment problem solved at the input: the query is drawn, as a typeset overlay, onto","authors_text":"Chunyi Lin, Guanhua Chen, Huimin Huang, Ruiluo Wu, Ruize Han, Wang Song, Xian Wu, Yifeng Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T08:40:41Z","title":"Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19944","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":"sha256:0ade51ea9fb4d90494c6f03d9a48a89677f1c04dc4290b9d6d3d55c753465613","target":"record","created_at":"2026-06-19T16:12:58Z","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":"022233364cd599373be0d27e38e952de8a71485193ba65acd01b81262b8edcc2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T08:40:41Z","title_canon_sha256":"ed7d2168fcb676b2b120f26ad63a21511db69327dcca17eec7577e3caeb5e600"},"schema_version":"1.0","source":{"id":"2606.19944","kind":"arxiv","version":1}},"canonical_sha256":"e3a180cd964e23912077fce63dbc039e2e6ea6c1bc6ada85facc2c6a0491c2db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3a180cd964e23912077fce63dbc039e2e6ea6c1bc6ada85facc2c6a0491c2db","first_computed_at":"2026-06-19T16:12:58.862677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:58.862677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZKisFihZRxtZqz6FQnoXaeBozZ/qQz3a/lnl+Of4cMX/6/fNsdqAXI9fJ2u0FVgvcNBG+cr2x7RGJzUcqQZXCg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:58.863085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ade51ea9fb4d90494c6f03d9a48a89677f1c04dc4290b9d6d3d55c753465613","sha256:7193f19309cc4508c027f19db8b4ad6372d0caec7b1dac6679514a6aeff8b8d6"],"state_sha256":"1665055da9b0ce6ebb1aadb3d6b5b5459534c61aaf8a171a80f92358c3c72027"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KN7NlaPA54vOsjt2dOV6sdnl3B9pFGfSUB5SsyQQ72J/oLA4yPG8aqitHxxUhoOBxu+SykWcUvH2aP9juSn2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T09:07:34.511555Z","bundle_sha256":"84eee04c1aed4e4979bc9f07f3fd25a104495bef37771b1642616b6ddca2f2c8"}}