{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:STFWCON6YYCYKK4KWJ2WMTXHQ2","short_pith_number":"pith:STFWCON6","canonical_record":{"source":{"id":"2502.01524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T17:01:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"5e2ca96b8d3fa7039b82e283cfb92618f145b2bd2b0e07331dc879f5b08bb4cc","abstract_canon_sha256":"0e423c2a381e5fb844cd084626a387b451893cc68112c1c68ec8d98f10dbcd79"},"schema_version":"1.0"},"canonical_sha256":"94cb6139bec605852b8ab275664ee7869b8ef3621a3ec7041d5277bbf7fade2a","source":{"kind":"arxiv","id":"2502.01524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01524","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01524v1","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01524","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"STFWCON6YYCY","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"STFWCON6YYCYKK4K","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"STFWCON6","created_at":"2026-07-05T10:09:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:STFWCON6YYCYKK4KWJ2WMTXHQ2","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T17:01:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"5e2ca96b8d3fa7039b82e283cfb92618f145b2bd2b0e07331dc879f5b08bb4cc","abstract_canon_sha256":"0e423c2a381e5fb844cd084626a387b451893cc68112c1c68ec8d98f10dbcd79"},"schema_version":"1.0"},"canonical_sha256":"94cb6139bec605852b8ab275664ee7869b8ef3621a3ec7041d5277bbf7fade2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:16.877179Z","signature_b64":"t6ASjDYN4uXbIWDHrJhAJn2m1S5edUt+EMZJdiMh85QrV+WQmXGMKfdK3sB3yVPubBqmlgIsfn3Fc4t1ra+4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94cb6139bec605852b8ab275664ee7869b8ef3621a3ec7041d5277bbf7fade2a","last_reissued_at":"2026-07-05T10:09:16.876733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:16.876733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01524","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":"2026-07-05T10:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nfn2iaF65CFlmLWXNL9blCcA8I7Db0fKJhFS+TL5ROtuAOePOYJ9K6FDrmHntX72OLN8K7GzUclXkAOA5hFjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:06:45.108435Z"},"content_sha256":"05015773ccd6a75428eb0f5d56b022cee97e45c722ad2b17742a5e3a276da2a4","schema_version":"1.0","event_id":"sha256:05015773ccd6a75428eb0f5d56b022cee97e45c722ad2b17742a5e3a276da2a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:STFWCON6YYCYKK4KWJ2WMTXHQ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficiently Integrate Large Language Models with Visual Perception: A Survey from the Training Paradigm Perspective","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Haoran Xie, S. Joe Qin, Xiaorui Ma","submitted_at":"2025-02-03T17:01:59Z","abstract_excerpt":"The integration of vision-language modalities has been a significant focus in multimodal learning, traditionally relying on Vision-Language Pretrained Models. However, with the advent of Large Language Models (LLMs), there has been a notable shift towards incorporating LLMs with vision modalities. Following this, the training paradigms for incorporating vision modalities into LLMs have evolved. Initially, the approach was to integrate the modalities through pretraining the modality integrator, named Single-stage Tuning. It has since branched out into methods focusing on performance enhancement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01524","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/2502.01524/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":"2026-07-05T10:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NcPkvHVDQN7HiQsRWxiBeR+0HQ+8YRPC8AdTYPQC3Cl3QY2JyHOI8GUUvXbAsaS2fwGQYO6XGcTvt8Xd4iacCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:06:45.109448Z"},"content_sha256":"127ebf8617ed87d0eea90274d4508ffb6b6090b5ec997414ecfa00cd38457bb7","schema_version":"1.0","event_id":"sha256:127ebf8617ed87d0eea90274d4508ffb6b6090b5ec997414ecfa00cd38457bb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/STFWCON6YYCYKK4KWJ2WMTXHQ2/bundle.json","state_url":"https://pith.science/pith/STFWCON6YYCYKK4KWJ2WMTXHQ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/STFWCON6YYCYKK4KWJ2WMTXHQ2/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":"2026-08-10T08:06:45Z","links":{"resolver":"https://pith.science/pith/STFWCON6YYCYKK4KWJ2WMTXHQ2","bundle":"https://pith.science/pith/STFWCON6YYCYKK4KWJ2WMTXHQ2/bundle.json","state":"https://pith.science/pith/STFWCON6YYCYKK4KWJ2WMTXHQ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/STFWCON6YYCYKK4KWJ2WMTXHQ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:STFWCON6YYCYKK4KWJ2WMTXHQ2","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":"0e423c2a381e5fb844cd084626a387b451893cc68112c1c68ec8d98f10dbcd79","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T17:01:59Z","title_canon_sha256":"5e2ca96b8d3fa7039b82e283cfb92618f145b2bd2b0e07331dc879f5b08bb4cc"},"schema_version":"1.0","source":{"id":"2502.01524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01524","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01524v1","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01524","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"STFWCON6YYCY","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"STFWCON6YYCYKK4K","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"STFWCON6","created_at":"2026-07-05T10:09:16Z"}],"graph_snapshots":[{"event_id":"sha256:127ebf8617ed87d0eea90274d4508ffb6b6090b5ec997414ecfa00cd38457bb7","target":"graph","created_at":"2026-07-05T10:09:16Z","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/2502.01524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of vision-language modalities has been a significant focus in multimodal learning, traditionally relying on Vision-Language Pretrained Models. However, with the advent of Large Language Models (LLMs), there has been a notable shift towards incorporating LLMs with vision modalities. Following this, the training paradigms for incorporating vision modalities into LLMs have evolved. Initially, the approach was to integrate the modalities through pretraining the modality integrator, named Single-stage Tuning. It has since branched out into methods focusing on performance enhancement","authors_text":"Haoran Xie, S. Joe Qin, Xiaorui Ma","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T17:01:59Z","title":"Efficiently Integrate Large Language Models with Visual Perception: A Survey from the Training Paradigm Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01524","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":"sha256:05015773ccd6a75428eb0f5d56b022cee97e45c722ad2b17742a5e3a276da2a4","target":"record","created_at":"2026-07-05T10:09:16Z","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":"0e423c2a381e5fb844cd084626a387b451893cc68112c1c68ec8d98f10dbcd79","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T17:01:59Z","title_canon_sha256":"5e2ca96b8d3fa7039b82e283cfb92618f145b2bd2b0e07331dc879f5b08bb4cc"},"schema_version":"1.0","source":{"id":"2502.01524","kind":"arxiv","version":1}},"canonical_sha256":"94cb6139bec605852b8ab275664ee7869b8ef3621a3ec7041d5277bbf7fade2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94cb6139bec605852b8ab275664ee7869b8ef3621a3ec7041d5277bbf7fade2a","first_computed_at":"2026-07-05T10:09:16.876733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:16.876733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t6ASjDYN4uXbIWDHrJhAJn2m1S5edUt+EMZJdiMh85QrV+WQmXGMKfdK3sB3yVPubBqmlgIsfn3Fc4t1ra+4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:16.877179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05015773ccd6a75428eb0f5d56b022cee97e45c722ad2b17742a5e3a276da2a4","sha256:127ebf8617ed87d0eea90274d4508ffb6b6090b5ec997414ecfa00cd38457bb7"],"state_sha256":"abbbbc3a67a5e10d62ca04e5fed3d934edb1529ff9ec34339a55b97e324374cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZt8AAAindRnzwezfwuKBnvtxuPFGyqtxrAQp5yiJXlcx+uADjDKfih2eY3YvzVM32CFLlKX/HDOCdNACQmhBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:06:45.133240Z","bundle_sha256":"aea80825a8e9846444d3766313d378e450e72c08d49ecd2e97f2620509d44488"}}