{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UNGBOKWOQ3MXD4OPCLD5CWG34M","short_pith_number":"pith:UNGBOKWO","canonical_record":{"source":{"id":"2406.02547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T17:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"fe959ceb73493d5af316f97b2613524ed70a220af71c05eee4e154105ae03eb0","abstract_canon_sha256":"d37cf99edec8b946047b5ab05b8e8f238577e5d9ad27acd3faf3be7c15d6a249"},"schema_version":"1.0"},"canonical_sha256":"a34c172ace86d971f1cf12c7d158dbe31129c9859bc26baf6fbaf3e044d52c76","source":{"kind":"arxiv","id":"2406.02547","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02547","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02547v1","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02547","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"UNGBOKWOQ3MX","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"UNGBOKWOQ3MXD4OP","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"UNGBOKWO","created_at":"2026-07-05T08:27:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UNGBOKWOQ3MXD4OPCLD5CWG34M","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T17:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"fe959ceb73493d5af316f97b2613524ed70a220af71c05eee4e154105ae03eb0","abstract_canon_sha256":"d37cf99edec8b946047b5ab05b8e8f238577e5d9ad27acd3faf3be7c15d6a249"},"schema_version":"1.0"},"canonical_sha256":"a34c172ace86d971f1cf12c7d158dbe31129c9859bc26baf6fbaf3e044d52c76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:21.113234Z","signature_b64":"nAsnfhptNn0+SDJ/a8T6dKe+GlLMbNa1pcl8s6C3w1brTCX8cQQvnGtAMtEnqLaONITKqHCahnixeZ9IikJmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a34c172ace86d971f1cf12c7d158dbe31129c9859bc26baf6fbaf3e044d52c76","last_reissued_at":"2026-07-05T08:27:21.112828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:21.112828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02547","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":"2026-07-05T08:27:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCuMzS66xipu/hwyZvuOC5NT7SOygaBoPtxEH1KlTZzf28R4OmuZn5OvS0MuyKsKlwkPniBc2Ye+7GCqd2v5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:39:48.882463Z"},"content_sha256":"f3c80db3c367650f9e46352442e2b02226640c926a0a84940eece3d07e6bfa93","schema_version":"1.0","event_id":"sha256:f3c80db3c367650f9e46352442e2b02226640c926a0a84940eece3d07e6bfa93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UNGBOKWOQ3MXD4OPCLD5CWG34M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Lijuan Wang, Linjie Li, Mike Zheng Shou, Min Li, Yiqi Lin","submitted_at":"2024-06-04T17:59:25Z","abstract_excerpt":"Training models with longer in-context lengths is a significant challenge for multimodal model due to substantial GPU memory and computational costs. This exploratory study does not present state-of-the-art models; rather, it introduces an innovative method designed to increase in-context text length in multi-modality large language models (MLLMs) efficiently. We present Visualized In-Context Text Processing (VisInContext), which processes long in-context text using visual tokens. This technique significantly reduces GPU memory usage and floating point operations (FLOPs) for both training and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02547","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/2406.02547/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":"2026-07-05T08:27:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XaVqaxqxfTUsPyHGqHtV/JPTMxDiphElF4yoenDLrezXvH8TlKFMWErtu/WjlhrswPuWm8otX6pYBL9YXWHKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:39:48.882957Z"},"content_sha256":"b8efcfcbfaef7c295fe8c68301797b57cd924229d60cd5d5790e7b2e6299a03b","schema_version":"1.0","event_id":"sha256:b8efcfcbfaef7c295fe8c68301797b57cd924229d60cd5d5790e7b2e6299a03b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNGBOKWOQ3MXD4OPCLD5CWG34M/bundle.json","state_url":"https://pith.science/pith/UNGBOKWOQ3MXD4OPCLD5CWG34M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNGBOKWOQ3MXD4OPCLD5CWG34M/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":"2026-08-11T20:39:48Z","links":{"resolver":"https://pith.science/pith/UNGBOKWOQ3MXD4OPCLD5CWG34M","bundle":"https://pith.science/pith/UNGBOKWOQ3MXD4OPCLD5CWG34M/bundle.json","state":"https://pith.science/pith/UNGBOKWOQ3MXD4OPCLD5CWG34M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNGBOKWOQ3MXD4OPCLD5CWG34M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UNGBOKWOQ3MXD4OPCLD5CWG34M","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":"d37cf99edec8b946047b5ab05b8e8f238577e5d9ad27acd3faf3be7c15d6a249","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T17:59:25Z","title_canon_sha256":"fe959ceb73493d5af316f97b2613524ed70a220af71c05eee4e154105ae03eb0"},"schema_version":"1.0","source":{"id":"2406.02547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02547","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02547v1","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02547","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"UNGBOKWOQ3MX","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"UNGBOKWOQ3MXD4OP","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"UNGBOKWO","created_at":"2026-07-05T08:27:21Z"}],"graph_snapshots":[{"event_id":"sha256:b8efcfcbfaef7c295fe8c68301797b57cd924229d60cd5d5790e7b2e6299a03b","target":"graph","created_at":"2026-07-05T08:27:21Z","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/2406.02547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training models with longer in-context lengths is a significant challenge for multimodal model due to substantial GPU memory and computational costs. This exploratory study does not present state-of-the-art models; rather, it introduces an innovative method designed to increase in-context text length in multi-modality large language models (MLLMs) efficiently. We present Visualized In-Context Text Processing (VisInContext), which processes long in-context text using visual tokens. This technique significantly reduces GPU memory usage and floating point operations (FLOPs) for both training and ","authors_text":"Alex Jinpeng Wang, Lijuan Wang, Linjie Li, Mike Zheng Shou, Min Li, Yiqi Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T17:59:25Z","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02547","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:f3c80db3c367650f9e46352442e2b02226640c926a0a84940eece3d07e6bfa93","target":"record","created_at":"2026-07-05T08:27:21Z","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":"d37cf99edec8b946047b5ab05b8e8f238577e5d9ad27acd3faf3be7c15d6a249","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T17:59:25Z","title_canon_sha256":"fe959ceb73493d5af316f97b2613524ed70a220af71c05eee4e154105ae03eb0"},"schema_version":"1.0","source":{"id":"2406.02547","kind":"arxiv","version":1}},"canonical_sha256":"a34c172ace86d971f1cf12c7d158dbe31129c9859bc26baf6fbaf3e044d52c76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a34c172ace86d971f1cf12c7d158dbe31129c9859bc26baf6fbaf3e044d52c76","first_computed_at":"2026-07-05T08:27:21.112828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:21.112828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nAsnfhptNn0+SDJ/a8T6dKe+GlLMbNa1pcl8s6C3w1brTCX8cQQvnGtAMtEnqLaONITKqHCahnixeZ9IikJmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:21.113234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3c80db3c367650f9e46352442e2b02226640c926a0a84940eece3d07e6bfa93","sha256:b8efcfcbfaef7c295fe8c68301797b57cd924229d60cd5d5790e7b2e6299a03b"],"state_sha256":"1e35003366c536725fbfcbf399036feef409a8f2d259ddb926ac71c78cb86d9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qmvvQGRQbXrYdza6oPu5uXqCeSVaoA/6rswVeznntj0CuunXAeSvqmEa6uRK5/p3KQjMMwJSTresJOJrHK+pAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:39:48.888939Z","bundle_sha256":"4837116faa57a2e897b089bf9c1dc20e85bd5eda5fcd800e1bee05febe928c08"}}