{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2MDWIO54IMNZS5WJ2FQWCBQAYU","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":"9db99437ba6c0ee9e0f3a5e25705d3db191d1fcccc1f9e3c846af0135cef2a00","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-17T14:13:20Z","title_canon_sha256":"de80349282f572c9fa00c20edffd50dff7b3e77ca315e2ab5d744bcba935d75f"},"schema_version":"1.0","source":{"id":"2509.14001","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.14001","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.14001v5","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.14001","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"2MDWIO54IMNZ","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"2MDWIO54IMNZS5WJ","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"2MDWIO54","created_at":"2026-06-24T00:14:20Z"}],"graph_snapshots":[{"event_id":"sha256:9307dd60477e867ec97cded871c13fca27b8b3061d86fcb3857ac4a8f4450cb4","target":"graph","created_at":"2026-06-24T00:14:20Z","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/2509.14001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples. Lightweight models often struggle in this setting due to their weak semantic priors, while large vision-language models (VLMs) offer strong object-level understanding but are too computationally demanding for real-time or on-device applications. We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a distillation framework that transfers multimodal region-level knowledge from a frozen VLM teacher into a lightweight vision-only detector. MO","authors_text":"Elena Camuffo, Francesco Barbato, Mete Ozay, Simone Milani, Umberto Michieli","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-17T14:13:20Z","title":"MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.14001","kind":"arxiv","version":5},"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":"sha256:458d69a11d9cf6e9e5ac969a87b5c25f9a9ddfe0a2e176762ea05b778e58ae01","target":"record","created_at":"2026-06-24T00:14:20Z","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":"9db99437ba6c0ee9e0f3a5e25705d3db191d1fcccc1f9e3c846af0135cef2a00","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-17T14:13:20Z","title_canon_sha256":"de80349282f572c9fa00c20edffd50dff7b3e77ca315e2ab5d744bcba935d75f"},"schema_version":"1.0","source":{"id":"2509.14001","kind":"arxiv","version":5}},"canonical_sha256":"d307643bbc431b9976c9d161610600c533d2567d450fa851b98f3e0279b08f1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d307643bbc431b9976c9d161610600c533d2567d450fa851b98f3e0279b08f1c","first_computed_at":"2026-06-24T00:14:20.952029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T00:14:20.952029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nZMVKLz7WGZlHeld/fpx2tlSCPGakj0oWuJvp9dH+rEMV4qFn2QAuduuLmGTqQ+8DSSk/0owAtzDaF0Ip8NZBA==","signature_status":"signed_v1","signed_at":"2026-06-24T00:14:20.952532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.14001","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:458d69a11d9cf6e9e5ac969a87b5c25f9a9ddfe0a2e176762ea05b778e58ae01","sha256:9307dd60477e867ec97cded871c13fca27b8b3061d86fcb3857ac4a8f4450cb4"],"state_sha256":"e504d5c6c13f42e632a377083c86595a80637c56f5c02c67ad40e4f92844cf25"}