{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TY3LLDH2DV2NGCDBIMDYCNMBC2","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":"99e663374a7d8a5014c1025a23916b863c9a60e869bc9073d14fc00aecf1e9c4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T05:41:26Z","title_canon_sha256":"7ff074c2efb7d6a4c52e3a0e4a0f72fa5a52911c8049c2f2bfc14225a624947f"},"schema_version":"1.0","source":{"id":"2505.23121","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23121","created_at":"2026-07-05T11:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23121v2","created_at":"2026-07-05T11:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23121","created_at":"2026-07-05T11:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"TY3LLDH2DV2N","created_at":"2026-07-05T11:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"TY3LLDH2DV2NGCDB","created_at":"2026-07-05T11:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"TY3LLDH2","created_at":"2026-07-05T11:38:51Z"}],"graph_snapshots":[{"event_id":"sha256:a968e49f9736760be9b21dacf4df0dc2730c6b1981a9be37bccb65f31bfaa4f1","target":"graph","created_at":"2026-07-05T11:38:51Z","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/2505.23121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models have demonstrated remarkable zero-shot abilities and powerful image-understanding capabilities. However, the existing open-source multi-modal models suffer from the weak capability of multi-turn interaction, especially for long contexts. To address the issue, we first introduce a context modeling module, termed ContextQFormer, which utilizes a memory block to enhance the presentation of contextual information. Furthermore, to facilitate further research, we carefully build a new multi-turn multi-modal dialogue dataset (TMDialog) for pre-training, instruction-t","authors_text":"Haitao Leng, Qingjie Liu, Shaoguo Liu, Tingting Gao, Yiming Lei, Yunhong Wang, Zeming Liu, Zhizheng Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T05:41:26Z","title":"ContextQFormer: A New Context Modeling Method for Multi-Turn Multi-Modal Conversations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23121","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":"sha256:0c7a8ab3b1d0ef0cb035d4808f194fed0d9a987389956703d86f4805961278bc","target":"record","created_at":"2026-07-05T11:38:51Z","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":"99e663374a7d8a5014c1025a23916b863c9a60e869bc9073d14fc00aecf1e9c4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T05:41:26Z","title_canon_sha256":"7ff074c2efb7d6a4c52e3a0e4a0f72fa5a52911c8049c2f2bfc14225a624947f"},"schema_version":"1.0","source":{"id":"2505.23121","kind":"arxiv","version":2}},"canonical_sha256":"9e36b58cfa1d74d30861430781358116b79304af7431f34d32824ca6f8619102","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e36b58cfa1d74d30861430781358116b79304af7431f34d32824ca6f8619102","first_computed_at":"2026-07-05T11:38:51.561861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:51.561861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jlVahZUZr6mcyf5rGPD06NEGo0NCxELz8xt4xvsHjL5Ooju6k7KavGyVGhSlwkSJiUx+642R385l2TOcYVjnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:51.562280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23121","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c7a8ab3b1d0ef0cb035d4808f194fed0d9a987389956703d86f4805961278bc","sha256:a968e49f9736760be9b21dacf4df0dc2730c6b1981a9be37bccb65f31bfaa4f1"],"state_sha256":"30fb0fd9f74a1117f05032f87d7a7ffe5c566392ed5b8660e949be70a0a94969"}