{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ROYWABARQVVE72ND5G5DFCCQKT","short_pith_number":"pith:ROYWABAR","canonical_record":{"source":{"id":"2407.08279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T08:28:40Z","cross_cats_sorted":[],"title_canon_sha256":"247af9c12f137fd1f715a5602acba36fd1d71d84badf065e1e073f5266c316cb","abstract_canon_sha256":"73695bccfd32ad881faa8d1a4082d30a3b1e2292298e66db648c6a9ac0e55477"},"schema_version":"1.0"},"canonical_sha256":"8bb1600411856a4fe9a3e9ba32885054f771b31420565c640390a8429932fe54","source":{"kind":"arxiv","id":"2407.08279","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08279","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08279v1","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08279","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"ROYWABARQVVE","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"ROYWABARQVVE72ND","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"ROYWABAR","created_at":"2026-07-05T11:44:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ROYWABARQVVE72ND5G5DFCCQKT","target":"record","payload":{"canonical_record":{"source":{"id":"2407.08279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T08:28:40Z","cross_cats_sorted":[],"title_canon_sha256":"247af9c12f137fd1f715a5602acba36fd1d71d84badf065e1e073f5266c316cb","abstract_canon_sha256":"73695bccfd32ad881faa8d1a4082d30a3b1e2292298e66db648c6a9ac0e55477"},"schema_version":"1.0"},"canonical_sha256":"8bb1600411856a4fe9a3e9ba32885054f771b31420565c640390a8429932fe54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:40.186068Z","signature_b64":"8I1JPk4ANb/NnTMEFGiBWOgzqhmXrMRNXCEFzJbEcPib9pFurMX4SunoYQb0IErekdGjK25gU0xpXG6kQ+jBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bb1600411856a4fe9a3e9ba32885054f771b31420565c640390a8429932fe54","last_reissued_at":"2026-07-05T11:44:40.185576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:40.185576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.08279","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":"2026-07-05T11:44:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XcQjn5OniLzGP/e2u1nryoOtmSrFFpGfHLptBBHOvGvmtb9ydAbLquAY44ZShEhYrF3fz9zZJmwSU9VNPYYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:48:50.527523Z"},"content_sha256":"03e79176a222141bdcf76587bba3a432e41582bc2465af10af992579587257eb","schema_version":"1.0","event_id":"sha256:03e79176a222141bdcf76587bba3a432e41582bc2465af10af992579587257eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ROYWABARQVVE72ND5G5DFCCQKT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrii Krutsylo, Clea Rebillard, Julio Hurtado, Lucia Passaro, Vincenzo Lomonaco","submitted_at":"2024-07-11T08:28:40Z","abstract_excerpt":"Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices. Visual models that are continually updated through supervised learning are often prone to overfitting, catastrophic forgetting, and biased representations. On the other hand, large language models contain knowledge about multiple concepts and their relations, which can foster a more robust, informed and coherent learning process. This work proposes Continual Visual Mapping (CVM), an approach that continually ground"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08279","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/2407.08279/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":"2026-07-05T11:44:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wTI83/WS9bELkrY4PFGVrA2obeKNZw9kZ+0KKZMXZPHcWT7k+7iPKCDdmaT7q4pWM9VHkfCUxaCx+GkZxXKSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:48:50.527906Z"},"content_sha256":"b375f0481fa5ea2e69d13081b391be6d81d38ace850680fbf0954145eec38618","schema_version":"1.0","event_id":"sha256:b375f0481fa5ea2e69d13081b391be6d81d38ace850680fbf0954145eec38618"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ROYWABARQVVE72ND5G5DFCCQKT/bundle.json","state_url":"https://pith.science/pith/ROYWABARQVVE72ND5G5DFCCQKT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ROYWABARQVVE72ND5G5DFCCQKT/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":"2026-07-09T06:48:50Z","links":{"resolver":"https://pith.science/pith/ROYWABARQVVE72ND5G5DFCCQKT","bundle":"https://pith.science/pith/ROYWABARQVVE72ND5G5DFCCQKT/bundle.json","state":"https://pith.science/pith/ROYWABARQVVE72ND5G5DFCCQKT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ROYWABARQVVE72ND5G5DFCCQKT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ROYWABARQVVE72ND5G5DFCCQKT","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":"73695bccfd32ad881faa8d1a4082d30a3b1e2292298e66db648c6a9ac0e55477","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T08:28:40Z","title_canon_sha256":"247af9c12f137fd1f715a5602acba36fd1d71d84badf065e1e073f5266c316cb"},"schema_version":"1.0","source":{"id":"2407.08279","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08279","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08279v1","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08279","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"ROYWABARQVVE","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"ROYWABARQVVE72ND","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"ROYWABAR","created_at":"2026-07-05T11:44:40Z"}],"graph_snapshots":[{"event_id":"sha256:b375f0481fa5ea2e69d13081b391be6d81d38ace850680fbf0954145eec38618","target":"graph","created_at":"2026-07-05T11:44:40Z","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/2407.08279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices. Visual models that are continually updated through supervised learning are often prone to overfitting, catastrophic forgetting, and biased representations. On the other hand, large language models contain knowledge about multiple concepts and their relations, which can foster a more robust, informed and coherent learning process. This work proposes Continual Visual Mapping (CVM), an approach that continually ground","authors_text":"Andrii Krutsylo, Clea Rebillard, Julio Hurtado, Lucia Passaro, Vincenzo Lomonaco","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T08:28:40Z","title":"Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08279","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":"sha256:03e79176a222141bdcf76587bba3a432e41582bc2465af10af992579587257eb","target":"record","created_at":"2026-07-05T11:44:40Z","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":"73695bccfd32ad881faa8d1a4082d30a3b1e2292298e66db648c6a9ac0e55477","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T08:28:40Z","title_canon_sha256":"247af9c12f137fd1f715a5602acba36fd1d71d84badf065e1e073f5266c316cb"},"schema_version":"1.0","source":{"id":"2407.08279","kind":"arxiv","version":1}},"canonical_sha256":"8bb1600411856a4fe9a3e9ba32885054f771b31420565c640390a8429932fe54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bb1600411856a4fe9a3e9ba32885054f771b31420565c640390a8429932fe54","first_computed_at":"2026-07-05T11:44:40.185576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:40.185576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8I1JPk4ANb/NnTMEFGiBWOgzqhmXrMRNXCEFzJbEcPib9pFurMX4SunoYQb0IErekdGjK25gU0xpXG6kQ+jBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:40.186068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08279","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03e79176a222141bdcf76587bba3a432e41582bc2465af10af992579587257eb","sha256:b375f0481fa5ea2e69d13081b391be6d81d38ace850680fbf0954145eec38618"],"state_sha256":"c63d79ce063107ada835063b0588d0d2c659b46e259b55aeae12b660a69eb16f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0GpgJkXNV0BqbwqrN7ji0s24wdWyP0c1ulnnX6lkKTAgABuv9uHlF78snErfzer2F5Lbm+OZuf4FZ8JKsl2wAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:48:50.530563Z","bundle_sha256":"36862dd6f740c5302fd3ff15255f3ddb9f6258f249e206014870abd3f5a8934b"}}