{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2GSDZXB5ZZ24MWD2H6PKELIWTL","short_pith_number":"pith:2GSDZXB5","canonical_record":{"source":{"id":"2411.16863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T19:01:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"4bdbd2b44a1229b36f20dd80be5d19aefb35c8a4a00d88e36c095796ea57356d","abstract_canon_sha256":"72df1d6aacdcee159d61dd49d3bef0851fb1dd8b8d8e271875747b358c4077ca"},"schema_version":"1.0"},"canonical_sha256":"d1a43cdc3dce75c6587a3f9ea22d169afd9e13646415d910ee7522bbca58e882","source":{"kind":"arxiv","id":"2411.16863","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16863","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16863v2","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16863","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"2GSDZXB5ZZ24","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"pith_short_16","alias_value":"2GSDZXB5ZZ24MWD2","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"pith_short_8","alias_value":"2GSDZXB5","created_at":"2026-07-05T10:43:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2GSDZXB5ZZ24MWD2H6PKELIWTL","target":"record","payload":{"canonical_record":{"source":{"id":"2411.16863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T19:01:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"4bdbd2b44a1229b36f20dd80be5d19aefb35c8a4a00d88e36c095796ea57356d","abstract_canon_sha256":"72df1d6aacdcee159d61dd49d3bef0851fb1dd8b8d8e271875747b358c4077ca"},"schema_version":"1.0"},"canonical_sha256":"d1a43cdc3dce75c6587a3f9ea22d169afd9e13646415d910ee7522bbca58e882","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:03.321495Z","signature_b64":"j7Y4/+JQ86kZVhpxfFHqNDP1S0CYMz6IYA9czPPpqPiNeztOdzB+IyPZUQb26/1ZDy+IIqRtYCOUR9VX9M/fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1a43cdc3dce75c6587a3f9ea22d169afd9e13646415d910ee7522bbca58e882","last_reissued_at":"2026-07-05T10:43:03.321020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:03.321020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.16863","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fIetrTwjhP5Ag9IeABwCL2tHLqxP8hN/9fIToFU0uKdwgjXO/Y5JAa4GTymOqZhZGp7lpiAu0/gCUtvBEKIBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:58:18.077092Z"},"content_sha256":"896ef5d90ba47ccb9b4a8bcb4256557ddf6762bb72559fa1c9c3d21ec583cec6","schema_version":"1.0","event_id":"sha256:896ef5d90ba47ccb9b4a8bcb4256557ddf6762bb72559fa1c9c3d21ec583cec6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2GSDZXB5ZZ24MWD2H6PKELIWTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Federico Cocchi, Lorenzo Baraldi, Marcella Cornia, Nicholas Moratelli, Rita Cucchiara","submitted_at":"2024-11-25T19:01:03Z","abstract_excerpt":"Multimodal LLMs (MLLMs) are the natural extension of large language models to handle multimodal inputs, combining text and image data. They have recently garnered attention due to their capability to address complex tasks involving both modalities. However, their effectiveness is limited to the knowledge acquired during training, which restricts their practical utility. In this work, we introduce a novel method to enhance the adaptability of MLLMs by integrating external knowledge sources. Our proposed model, Reflective LLaVA (ReflectiVA), utilizes reflective tokens to dynamically determine th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16863","kind":"arxiv","version":2},"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/2411.16863/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":"2026-07-05T10:43:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rR5H01yHDMmwQweg70it4qKuI4rcwHyM8FyKKwZMldTlMooWdWKvgSKczbTqhPqbT/SOXN/isk7ruvvdoMgUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:58:18.077599Z"},"content_sha256":"90c8704a3f0c01dafacf63c979d240957a332384060e9632ba1b419e3f0820fa","schema_version":"1.0","event_id":"sha256:90c8704a3f0c01dafacf63c979d240957a332384060e9632ba1b419e3f0820fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2GSDZXB5ZZ24MWD2H6PKELIWTL/bundle.json","state_url":"https://pith.science/pith/2GSDZXB5ZZ24MWD2H6PKELIWTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2GSDZXB5ZZ24MWD2H6PKELIWTL/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":"2026-08-08T22:58:18Z","links":{"resolver":"https://pith.science/pith/2GSDZXB5ZZ24MWD2H6PKELIWTL","bundle":"https://pith.science/pith/2GSDZXB5ZZ24MWD2H6PKELIWTL/bundle.json","state":"https://pith.science/pith/2GSDZXB5ZZ24MWD2H6PKELIWTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2GSDZXB5ZZ24MWD2H6PKELIWTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2GSDZXB5ZZ24MWD2H6PKELIWTL","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":"72df1d6aacdcee159d61dd49d3bef0851fb1dd8b8d8e271875747b358c4077ca","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T19:01:03Z","title_canon_sha256":"4bdbd2b44a1229b36f20dd80be5d19aefb35c8a4a00d88e36c095796ea57356d"},"schema_version":"1.0","source":{"id":"2411.16863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16863","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16863v2","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16863","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"2GSDZXB5ZZ24","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"pith_short_16","alias_value":"2GSDZXB5ZZ24MWD2","created_at":"2026-07-05T10:43:03Z"},{"alias_kind":"pith_short_8","alias_value":"2GSDZXB5","created_at":"2026-07-05T10:43:03Z"}],"graph_snapshots":[{"event_id":"sha256:90c8704a3f0c01dafacf63c979d240957a332384060e9632ba1b419e3f0820fa","target":"graph","created_at":"2026-07-05T10:43:03Z","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/2411.16863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal LLMs (MLLMs) are the natural extension of large language models to handle multimodal inputs, combining text and image data. They have recently garnered attention due to their capability to address complex tasks involving both modalities. However, their effectiveness is limited to the knowledge acquired during training, which restricts their practical utility. In this work, we introduce a novel method to enhance the adaptability of MLLMs by integrating external knowledge sources. Our proposed model, Reflective LLaVA (ReflectiVA), utilizes reflective tokens to dynamically determine th","authors_text":"Federico Cocchi, Lorenzo Baraldi, Marcella Cornia, Nicholas Moratelli, Rita Cucchiara","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T19:01:03Z","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16863","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":"sha256:896ef5d90ba47ccb9b4a8bcb4256557ddf6762bb72559fa1c9c3d21ec583cec6","target":"record","created_at":"2026-07-05T10:43:03Z","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":"72df1d6aacdcee159d61dd49d3bef0851fb1dd8b8d8e271875747b358c4077ca","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T19:01:03Z","title_canon_sha256":"4bdbd2b44a1229b36f20dd80be5d19aefb35c8a4a00d88e36c095796ea57356d"},"schema_version":"1.0","source":{"id":"2411.16863","kind":"arxiv","version":2}},"canonical_sha256":"d1a43cdc3dce75c6587a3f9ea22d169afd9e13646415d910ee7522bbca58e882","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1a43cdc3dce75c6587a3f9ea22d169afd9e13646415d910ee7522bbca58e882","first_computed_at":"2026-07-05T10:43:03.321020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:03.321020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j7Y4/+JQ86kZVhpxfFHqNDP1S0CYMz6IYA9czPPpqPiNeztOdzB+IyPZUQb26/1ZDy+IIqRtYCOUR9VX9M/fDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:03.321495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:896ef5d90ba47ccb9b4a8bcb4256557ddf6762bb72559fa1c9c3d21ec583cec6","sha256:90c8704a3f0c01dafacf63c979d240957a332384060e9632ba1b419e3f0820fa"],"state_sha256":"89bf116ae053fe3a956d618a61a19f435fe49b6f7fe693a3bba9772e12171be7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F5+fIa7KEV0wQmlPJk55bZ8H8eHpkrWTskOKRZQszSqUu7B1Qvydf2IJJ66VBZAxdj5kquQosKXkELRjC2GZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:58:18.082461Z","bundle_sha256":"2a78556b18aa0698aa91a410bb7c4e3c327a9f81496a17bd7dae299252827df1"}}