{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2MDWIO54IMNZS5WJ2FQWCBQAYU","short_pith_number":"pith:2MDWIO54","schema_version":"1.0","canonical_sha256":"d307643bbc431b9976c9d161610600c533d2567d450fa851b98f3e0279b08f1c","source":{"kind":"arxiv","id":"2509.14001","version":5},"attestation_state":"computed","paper":{"title":"MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Elena Camuffo, Francesco Barbato, Mete Ozay, Simone Milani, Umberto Michieli","submitted_at":"2025-09-17T14:13:20Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.14001","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-17T14:13:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"de80349282f572c9fa00c20edffd50dff7b3e77ca315e2ab5d744bcba935d75f","abstract_canon_sha256":"9db99437ba6c0ee9e0f3a5e25705d3db191d1fcccc1f9e3c846af0135cef2a00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:20.952532Z","signature_b64":"nZMVKLz7WGZlHeld/fpx2tlSCPGakj0oWuJvp9dH+rEMV4qFn2QAuduuLmGTqQ+8DSSk/0owAtzDaF0Ip8NZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d307643bbc431b9976c9d161610600c533d2567d450fa851b98f3e0279b08f1c","last_reissued_at":"2026-06-24T00:14:20.952029Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:20.952029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Elena Camuffo, Francesco Barbato, Mete Ozay, Simone Milani, Umberto Michieli","submitted_at":"2025-09-17T14:13:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.14001","kind":"arxiv","version":5},"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/2509.14001/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.14001","created_at":"2026-06-24T00:14:20.952087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.14001v5","created_at":"2026-06-24T00:14:20.952087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.14001","created_at":"2026-06-24T00:14:20.952087+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MDWIO54IMNZ","created_at":"2026-06-24T00:14:20.952087+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MDWIO54IMNZS5WJ","created_at":"2026-06-24T00:14:20.952087+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MDWIO54","created_at":"2026-06-24T00:14:20.952087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU","json":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU.json","graph_json":"https://pith.science/api/pith-number/2MDWIO54IMNZS5WJ2FQWCBQAYU/graph.json","events_json":"https://pith.science/api/pith-number/2MDWIO54IMNZS5WJ2FQWCBQAYU/events.json","paper":"https://pith.science/paper/2MDWIO54"},"agent_actions":{"view_html":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU","download_json":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU.json","view_paper":"https://pith.science/paper/2MDWIO54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.14001&json=true","fetch_graph":"https://pith.science/api/pith-number/2MDWIO54IMNZS5WJ2FQWCBQAYU/graph.json","fetch_events":"https://pith.science/api/pith-number/2MDWIO54IMNZS5WJ2FQWCBQAYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU/action/storage_attestation","attest_author":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU/action/author_attestation","sign_citation":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU/action/citation_signature","submit_replication":"https://pith.science/pith/2MDWIO54IMNZS5WJ2FQWCBQAYU/action/replication_record"}},"created_at":"2026-06-24T00:14:20.952087+00:00","updated_at":"2026-06-24T00:14:20.952087+00:00"}