{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BP2MKXXL2SCTJX3KA6WVAJKXEW","short_pith_number":"pith:BP2MKXXL","canonical_record":{"source":{"id":"2507.04590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T00:51:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"770639c941a8e127cae28198abdbfa05641bba94f2b0b7b476930fcb69512fc0","abstract_canon_sha256":"241f92326e99282f30f2da9a6ec904fef1d1d8d4eafb4475ea3030afd9c95b12"},"schema_version":"1.0"},"canonical_sha256":"0bf4c55eebd48534df6a07ad502557259f6c207ce686c1589db71f712631929b","source":{"kind":"arxiv","id":"2507.04590","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04590","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04590v1","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04590","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"BP2MKXXL2SCT","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"BP2MKXXL2SCTJX3K","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"BP2MKXXL","created_at":"2026-05-18T14:03:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BP2MKXXL2SCTJX3KA6WVAJKXEW","target":"record","payload":{"canonical_record":{"source":{"id":"2507.04590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T00:51:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"770639c941a8e127cae28198abdbfa05641bba94f2b0b7b476930fcb69512fc0","abstract_canon_sha256":"241f92326e99282f30f2da9a6ec904fef1d1d8d4eafb4475ea3030afd9c95b12"},"schema_version":"1.0"},"canonical_sha256":"0bf4c55eebd48534df6a07ad502557259f6c207ce686c1589db71f712631929b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T14:03:49.029853Z","signature_b64":"iH8kHKCgwXA1LBHKwkZ3WlNU5V5nhDXSN/qDSKBdYB7GI99RcAuRrUzHzyhAxNwJoIIrvo3ATild9eZ/H3vYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf4c55eebd48534df6a07ad502557259f6c207ce686c1589db71f712631929b","last_reissued_at":"2026-05-18T14:03:49.027205Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T14:03:49.027205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.04590","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":"2026-05-18T14:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S5tGmRBaXR8N59hWnBU+o7sgvLcvjeAB6R+kyETi1xO1wRMrZmBv8ZrFI9nYPYKFdXCWzO+oVOnpp74wAhdgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:11:03.698343Z"},"content_sha256":"3899ed56154a6f5840ad28a0817237e44d380d23eaeff77058b806cb2b5e7147","schema_version":"1.0","event_id":"sha256:3899ed56154a6f5840ad28a0817237e44d380d23eaeff77058b806cb2b5e7147"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BP2MKXXL2SCTJX3KA6WVAJKXEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Can Qin, Mingyi Su, Ran Xu, Rui Meng, Semih Yavuz, Wenhu Chen, Xinyi Yang, Ye Liu, Yingbo Zhou, Yuepeng Fu, Zeyuan Chen, Ziyan Jiang","submitted_at":"2025-07-07T00:51:57Z","abstract_excerpt":"Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME are predominantly focused on natural images, with limited support for other visual forms such as videos and visual documents. This restricts their applicability in real-world scenarios, including AI agents, multi-modal search and recommendation, and retrieval-augmented generation (RAG). To close this gap, we propose VLM2Vec-V2, a unified framework for learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04590","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":""},"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":"2026-05-18T14:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eIiNq8xqm8s+IF9baGMm2lnSZUBSnwxsx1txdKwbdU7CGJiyzsj/1qhwqFP5heVr346Lf7Qn+s0/FNCmbJGJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:11:03.698966Z"},"content_sha256":"64b3e4fd47efb59683d4b7731d98faf3c92fc1de11b69593eec6686c03a53c6d","schema_version":"1.0","event_id":"sha256:64b3e4fd47efb59683d4b7731d98faf3c92fc1de11b69593eec6686c03a53c6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BP2MKXXL2SCTJX3KA6WVAJKXEW/bundle.json","state_url":"https://pith.science/pith/BP2MKXXL2SCTJX3KA6WVAJKXEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BP2MKXXL2SCTJX3KA6WVAJKXEW/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":"2026-05-27T08:11:03Z","links":{"resolver":"https://pith.science/pith/BP2MKXXL2SCTJX3KA6WVAJKXEW","bundle":"https://pith.science/pith/BP2MKXXL2SCTJX3KA6WVAJKXEW/bundle.json","state":"https://pith.science/pith/BP2MKXXL2SCTJX3KA6WVAJKXEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BP2MKXXL2SCTJX3KA6WVAJKXEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BP2MKXXL2SCTJX3KA6WVAJKXEW","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":"241f92326e99282f30f2da9a6ec904fef1d1d8d4eafb4475ea3030afd9c95b12","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T00:51:57Z","title_canon_sha256":"770639c941a8e127cae28198abdbfa05641bba94f2b0b7b476930fcb69512fc0"},"schema_version":"1.0","source":{"id":"2507.04590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04590","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04590v1","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04590","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"BP2MKXXL2SCT","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"BP2MKXXL2SCTJX3K","created_at":"2026-05-18T14:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"BP2MKXXL","created_at":"2026-05-18T14:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:64b3e4fd47efb59683d4b7731d98faf3c92fc1de11b69593eec6686c03a53c6d","target":"graph","created_at":"2026-05-18T14:03:49Z","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"},"paper":{"abstract_excerpt":"Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME are predominantly focused on natural images, with limited support for other visual forms such as videos and visual documents. This restricts their applicability in real-world scenarios, including AI agents, multi-modal search and recommendation, and retrieval-augmented generation (RAG). To close this gap, we propose VLM2Vec-V2, a unified framework for learn","authors_text":"Caiming Xiong, Can Qin, Mingyi Su, Ran Xu, Rui Meng, Semih Yavuz, Wenhu Chen, Xinyi Yang, Ye Liu, Yingbo Zhou, Yuepeng Fu, Zeyuan Chen, Ziyan Jiang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T00:51:57Z","title":"VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04590","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":"sha256:3899ed56154a6f5840ad28a0817237e44d380d23eaeff77058b806cb2b5e7147","target":"record","created_at":"2026-05-18T14:03:49Z","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":"241f92326e99282f30f2da9a6ec904fef1d1d8d4eafb4475ea3030afd9c95b12","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T00:51:57Z","title_canon_sha256":"770639c941a8e127cae28198abdbfa05641bba94f2b0b7b476930fcb69512fc0"},"schema_version":"1.0","source":{"id":"2507.04590","kind":"arxiv","version":1}},"canonical_sha256":"0bf4c55eebd48534df6a07ad502557259f6c207ce686c1589db71f712631929b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf4c55eebd48534df6a07ad502557259f6c207ce686c1589db71f712631929b","first_computed_at":"2026-05-18T14:03:49.027205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T14:03:49.027205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iH8kHKCgwXA1LBHKwkZ3WlNU5V5nhDXSN/qDSKBdYB7GI99RcAuRrUzHzyhAxNwJoIIrvo3ATild9eZ/H3vYBg==","signature_status":"signed_v1","signed_at":"2026-05-18T14:03:49.029853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3899ed56154a6f5840ad28a0817237e44d380d23eaeff77058b806cb2b5e7147","sha256:64b3e4fd47efb59683d4b7731d98faf3c92fc1de11b69593eec6686c03a53c6d"],"state_sha256":"e22a8b83bd853ff69385be031abf42dda6534b833f8d69293694f5a5dbfabeb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A/DXkRKjLcYRytmexJWTL8Ld0JZrnmQENIF1Rs4RukdRYcJlxcPBH80pfn+BbyjugNHh6ciSnKvRIOizdPRYCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T08:11:03.702401Z","bundle_sha256":"744647428daf584466adb9e533647efc3ace6cdb9cc1d9896d9ecdaed95a098d"}}