{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OWQVFKK34AXR7P3MTCMQPI5NX5","short_pith_number":"pith:OWQVFKK3","canonical_record":{"source":{"id":"2410.23089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T15:05:17Z","cross_cats_sorted":[],"title_canon_sha256":"dbf814e31ac9cdca372adff92a80091a2452560a5f46c5f23c8752891300c400","abstract_canon_sha256":"da610d6868732fa15240d4717e92d4df8da2e86528d60d304b9b3c4593f8e709"},"schema_version":"1.0"},"canonical_sha256":"75a152a95be02f1fbf6c989907a3adbf6d9b1587a2607797a46fc8b55777de96","source":{"kind":"arxiv","id":"2410.23089","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23089","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23089v1","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23089","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"pith_short_12","alias_value":"OWQVFKK34AXR","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"pith_short_16","alias_value":"OWQVFKK34AXR7P3M","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"pith_short_8","alias_value":"OWQVFKK3","created_at":"2026-07-05T09:28:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OWQVFKK34AXR7P3MTCMQPI5NX5","target":"record","payload":{"canonical_record":{"source":{"id":"2410.23089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T15:05:17Z","cross_cats_sorted":[],"title_canon_sha256":"dbf814e31ac9cdca372adff92a80091a2452560a5f46c5f23c8752891300c400","abstract_canon_sha256":"da610d6868732fa15240d4717e92d4df8da2e86528d60d304b9b3c4593f8e709"},"schema_version":"1.0"},"canonical_sha256":"75a152a95be02f1fbf6c989907a3adbf6d9b1587a2607797a46fc8b55777de96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:40.890465Z","signature_b64":"m6+p3tfiM+1cTcZSf95Gk1YaU6dNdd+AaLX4/HmizxF1gp1aaf6N6oAhW2GgpM1H3rAvaOCMLzMqADeYDeDbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75a152a95be02f1fbf6c989907a3adbf6d9b1587a2607797a46fc8b55777de96","last_reissued_at":"2026-07-05T09:28:40.889933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:40.889933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.23089","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":"2026-07-05T09:28:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UfKC+dePWXn9QE2VLj/R7ZL9fq1EKlSYRu68u9BormQqrdgXT0avtO6vvILw9jnQbsMj5NZW+WTMonnhOyHwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:27:09.536981Z"},"content_sha256":"3d440d1b4f051cb36b88a3af46f513771a25303ae7abad4b897ff0982f0dd3fe","schema_version":"1.0","event_id":"sha256:3d440d1b4f051cb36b88a3af46f513771a25303ae7abad4b897ff0982f0dd3fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OWQVFKK34AXR7P3MTCMQPI5NX5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Minxin Nie, Tianxiang Wu, Ziqiang Cao","submitted_at":"2024-10-30T15:05:17Z","abstract_excerpt":"The Multimodal Large Language Models (MLLMs) have activated the capabilitiesof Large Language Models (LLMs) in solving visual-language tasks by integratingvisual information. The prevailing approach in existing MLLMs involvesemploying an image encoder to extract visual features, converting thesefeatures into visual tokens via an adapter, and then integrating them with theprompt into the LLM. However, because the process of image encoding isprompt-agnostic, the extracted visual features only provide a coarsedescription of the image, impossible to focus on the requirements of theprompt. On one h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23089","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/2410.23089/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":"2026-07-05T09:28:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tgdkuStJdDwPw4Tei8ZEBFEpyFFpNqX38r3AeG1YFWjEPljoALvnQY0TwBb3iAvPWbhqqHLPG3qV5XaKhMbkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:27:09.537383Z"},"content_sha256":"f045c302f156f4c92b4c21bad147028313ff9c20131c4a99dd661cca4a81e23a","schema_version":"1.0","event_id":"sha256:f045c302f156f4c92b4c21bad147028313ff9c20131c4a99dd661cca4a81e23a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWQVFKK34AXR7P3MTCMQPI5NX5/bundle.json","state_url":"https://pith.science/pith/OWQVFKK34AXR7P3MTCMQPI5NX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWQVFKK34AXR7P3MTCMQPI5NX5/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":"2026-07-14T19:27:09Z","links":{"resolver":"https://pith.science/pith/OWQVFKK34AXR7P3MTCMQPI5NX5","bundle":"https://pith.science/pith/OWQVFKK34AXR7P3MTCMQPI5NX5/bundle.json","state":"https://pith.science/pith/OWQVFKK34AXR7P3MTCMQPI5NX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWQVFKK34AXR7P3MTCMQPI5NX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OWQVFKK34AXR7P3MTCMQPI5NX5","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":"da610d6868732fa15240d4717e92d4df8da2e86528d60d304b9b3c4593f8e709","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T15:05:17Z","title_canon_sha256":"dbf814e31ac9cdca372adff92a80091a2452560a5f46c5f23c8752891300c400"},"schema_version":"1.0","source":{"id":"2410.23089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23089","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23089v1","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23089","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"pith_short_12","alias_value":"OWQVFKK34AXR","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"pith_short_16","alias_value":"OWQVFKK34AXR7P3M","created_at":"2026-07-05T09:28:40Z"},{"alias_kind":"pith_short_8","alias_value":"OWQVFKK3","created_at":"2026-07-05T09:28:40Z"}],"graph_snapshots":[{"event_id":"sha256:f045c302f156f4c92b4c21bad147028313ff9c20131c4a99dd661cca4a81e23a","target":"graph","created_at":"2026-07-05T09:28:40Z","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/2410.23089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Multimodal Large Language Models (MLLMs) have activated the capabilitiesof Large Language Models (LLMs) in solving visual-language tasks by integratingvisual information. The prevailing approach in existing MLLMs involvesemploying an image encoder to extract visual features, converting thesefeatures into visual tokens via an adapter, and then integrating them with theprompt into the LLM. However, because the process of image encoding isprompt-agnostic, the extracted visual features only provide a coarsedescription of the image, impossible to focus on the requirements of theprompt. On one h","authors_text":"Minxin Nie, Tianxiang Wu, Ziqiang Cao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T15:05:17Z","title":"PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23089","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":"sha256:3d440d1b4f051cb36b88a3af46f513771a25303ae7abad4b897ff0982f0dd3fe","target":"record","created_at":"2026-07-05T09:28:40Z","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":"da610d6868732fa15240d4717e92d4df8da2e86528d60d304b9b3c4593f8e709","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T15:05:17Z","title_canon_sha256":"dbf814e31ac9cdca372adff92a80091a2452560a5f46c5f23c8752891300c400"},"schema_version":"1.0","source":{"id":"2410.23089","kind":"arxiv","version":1}},"canonical_sha256":"75a152a95be02f1fbf6c989907a3adbf6d9b1587a2607797a46fc8b55777de96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75a152a95be02f1fbf6c989907a3adbf6d9b1587a2607797a46fc8b55777de96","first_computed_at":"2026-07-05T09:28:40.889933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:40.889933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m6+p3tfiM+1cTcZSf95Gk1YaU6dNdd+AaLX4/HmizxF1gp1aaf6N6oAhW2GgpM1H3rAvaOCMLzMqADeYDeDbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:40.890465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d440d1b4f051cb36b88a3af46f513771a25303ae7abad4b897ff0982f0dd3fe","sha256:f045c302f156f4c92b4c21bad147028313ff9c20131c4a99dd661cca4a81e23a"],"state_sha256":"ab8a2f68d045a6eb303565de091b5bda37ac35fd634941d694000c46fd11c6f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M0Fo/mYEAFtDI8jSMnbhpqlXXi7PB8x91Y8JDC4tTNQCIrDGDxBVoaoIF+qKxj5ncDyjCTH/DMP4IOIN3CGJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T19:27:09.541019Z","bundle_sha256":"7d6bdcac1c744d554a60fe70cfdfde66f1201d36874dbe1091a514bd07ee9612"}}