{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DI5NKKSSDBDW6NCWJ4XE6IC3HH","short_pith_number":"pith:DI5NKKSS","canonical_record":{"source":{"id":"2402.10805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-02-16T16:31:46Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.IR"],"title_canon_sha256":"45859baab68f3be7843e2d4a375d6539f1850b44d16cb5c076497c9097990372","abstract_canon_sha256":"a90b36225a55b267b12fe4e52c38be8bdbf50fa6f56abf0121ce0af9c495c480"},"schema_version":"1.0"},"canonical_sha256":"1a3ad52a5218476f34564f2e4f205b39d83c35f84dd77b2253af96cfe4a6c555","source":{"kind":"arxiv","id":"2402.10805","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10805","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10805v1","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10805","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"DI5NKKSSDBDW","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"DI5NKKSSDBDW6NCW","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"DI5NKKSS","created_at":"2026-07-05T07:46:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DI5NKKSSDBDW6NCWJ4XE6IC3HH","target":"record","payload":{"canonical_record":{"source":{"id":"2402.10805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-02-16T16:31:46Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.IR"],"title_canon_sha256":"45859baab68f3be7843e2d4a375d6539f1850b44d16cb5c076497c9097990372","abstract_canon_sha256":"a90b36225a55b267b12fe4e52c38be8bdbf50fa6f56abf0121ce0af9c495c480"},"schema_version":"1.0"},"canonical_sha256":"1a3ad52a5218476f34564f2e4f205b39d83c35f84dd77b2253af96cfe4a6c555","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:00.859781Z","signature_b64":"J3ZcWGNSUQ0tv9/u2QP4JR2PjBuJQgKd7TV2luyssWqhfTD6q7WV3pvri5k5j1/YFut2C0PBKSh0QA2YYro3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a3ad52a5218476f34564f2e4f205b39d83c35f84dd77b2253af96cfe4a6c555","last_reissued_at":"2026-07-05T07:46:00.859357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:00.859357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.10805","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":"2026-07-05T07:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CqHrY7zF4U0mMywxnS6LGyoquxp0L4aT/nv69o+PgpWq9J4aGqO76kdXaAQeP6f6Z1ZPPYJpFPSND4XbZ5TIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:07:21.741607Z"},"content_sha256":"f98d6aae070e9a704771b509393ddf8eff93da16bb20bc410145db352076230a","schema_version":"1.0","event_id":"sha256:f98d6aae070e9a704771b509393ddf8eff93da16bb20bc410145db352076230a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DI5NKKSSDBDW6NCWJ4XE6IC3HH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.IR"],"primary_cat":"cs.MM","authors_text":"Leigang Qu, Liqiang Nie, Tat-Seng Chua, Wenjie Li, Wenjie Wang, Yongqi Li","submitted_at":"2024-02-16T16:31:46Z","abstract_excerpt":"The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable multimodal large language models (MLLMs) to memorize and recall images within their parameters. Given a user query for visual content, the MLLM is anticipated to \"recall\" the relevant image from its parameters as the response. Achieving this target presents notable challenges, including inbuilt visual memory and visual recall schemes within MLLMs. To address the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10805","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/2402.10805/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":"2026-07-05T07:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d7J/xI/BsI+ujMdpSXZn7II3Tqb3eoJDDpDIJCHo4YqdfNNG+ndXKx/8+4X6sN8dgZoJkYgjklh9bDNaHw3CBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:07:21.743888Z"},"content_sha256":"2afd1973e122c24d926ca5c2b7b5f49edd3d58327afdc3c80c2aef8d0e953473","schema_version":"1.0","event_id":"sha256:2afd1973e122c24d926ca5c2b7b5f49edd3d58327afdc3c80c2aef8d0e953473"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DI5NKKSSDBDW6NCWJ4XE6IC3HH/bundle.json","state_url":"https://pith.science/pith/DI5NKKSSDBDW6NCWJ4XE6IC3HH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DI5NKKSSDBDW6NCWJ4XE6IC3HH/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":"2026-08-11T17:07:21Z","links":{"resolver":"https://pith.science/pith/DI5NKKSSDBDW6NCWJ4XE6IC3HH","bundle":"https://pith.science/pith/DI5NKKSSDBDW6NCWJ4XE6IC3HH/bundle.json","state":"https://pith.science/pith/DI5NKKSSDBDW6NCWJ4XE6IC3HH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DI5NKKSSDBDW6NCWJ4XE6IC3HH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DI5NKKSSDBDW6NCWJ4XE6IC3HH","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":"a90b36225a55b267b12fe4e52c38be8bdbf50fa6f56abf0121ce0af9c495c480","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-02-16T16:31:46Z","title_canon_sha256":"45859baab68f3be7843e2d4a375d6539f1850b44d16cb5c076497c9097990372"},"schema_version":"1.0","source":{"id":"2402.10805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10805","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10805v1","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10805","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"DI5NKKSSDBDW","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"DI5NKKSSDBDW6NCW","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"DI5NKKSS","created_at":"2026-07-05T07:46:00Z"}],"graph_snapshots":[{"event_id":"sha256:2afd1973e122c24d926ca5c2b7b5f49edd3d58327afdc3c80c2aef8d0e953473","target":"graph","created_at":"2026-07-05T07:46:00Z","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/2402.10805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable multimodal large language models (MLLMs) to memorize and recall images within their parameters. Given a user query for visual content, the MLLM is anticipated to \"recall\" the relevant image from its parameters as the response. Achieving this target presents notable challenges, including inbuilt visual memory and visual recall schemes within MLLMs. To address the","authors_text":"Leigang Qu, Liqiang Nie, Tat-Seng Chua, Wenjie Li, Wenjie Wang, Yongqi Li","cross_cats":["cs.AI","cs.CL","cs.CV","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-02-16T16:31:46Z","title":"Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10805","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:f98d6aae070e9a704771b509393ddf8eff93da16bb20bc410145db352076230a","target":"record","created_at":"2026-07-05T07:46:00Z","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":"a90b36225a55b267b12fe4e52c38be8bdbf50fa6f56abf0121ce0af9c495c480","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-02-16T16:31:46Z","title_canon_sha256":"45859baab68f3be7843e2d4a375d6539f1850b44d16cb5c076497c9097990372"},"schema_version":"1.0","source":{"id":"2402.10805","kind":"arxiv","version":1}},"canonical_sha256":"1a3ad52a5218476f34564f2e4f205b39d83c35f84dd77b2253af96cfe4a6c555","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a3ad52a5218476f34564f2e4f205b39d83c35f84dd77b2253af96cfe4a6c555","first_computed_at":"2026-07-05T07:46:00.859357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:00.859357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J3ZcWGNSUQ0tv9/u2QP4JR2PjBuJQgKd7TV2luyssWqhfTD6q7WV3pvri5k5j1/YFut2C0PBKSh0QA2YYro3BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:00.859781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f98d6aae070e9a704771b509393ddf8eff93da16bb20bc410145db352076230a","sha256:2afd1973e122c24d926ca5c2b7b5f49edd3d58327afdc3c80c2aef8d0e953473"],"state_sha256":"2d197cbbf2e60865d834e17f48b57ed3d9672d9dd1e16bc02d2ba3044c99cc0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QVncxixxffuKhPx4i+smhkGQFa6pvn/H0ds/nTQJ8JFEpAx/tKohzC4wzMRCC2FYZ8hubLkK632mM+lJEAKCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:07:21.753993Z","bundle_sha256":"28a6596b7bc655ff2b0339090044be2d10194edf79dcbcc20a64ebe07be1364b"}}