{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XH4GLOEP3BBYLJQLDZMNDQZPGC","short_pith_number":"pith:XH4GLOEP","schema_version":"1.0","canonical_sha256":"b9f865b88fd84385a60b1e58d1c32f30977b7112850f8798d92c413047d75f47","source":{"kind":"arxiv","id":"2506.21080","version":1},"attestation_state":"computed","paper":{"title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Calvin Murdock, Dinesh Manocha, Ishwarya Ananthabhotla, Ruohan Gao, Sanjoy Chowdhury, Sayan Nag, Subrata Biswas, Tushar Nagarajan, Vamsi Krishna Ithapu, Yijun Qian","submitted_at":"2025-06-26T08:09:16Z","abstract_excerpt":"Modern perception models, particularly those designed for multisensory egocentric tasks, have achieved remarkable performance but often come with substantial computational costs. These high demands pose challenges for real-world deployment, especially in resource-constrained environments. In this paper, we introduce EgoAdapt, a framework that adaptively performs cross-modal distillation and policy learning to enable efficient inference across different egocentric perception tasks, including egocentric action recognition, active speaker localization, and behavior anticipation. Our proposed poli"},"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":"2506.21080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T08:09:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e6bee3728fa3d0a27529a330117719b5794b48007291e2c37a848fcc660ba41d","abstract_canon_sha256":"6ef4dae6b6ad522b81e0623e9b11a5180edcf1b036e0f1673e0154352a1e1e35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:39.783875Z","signature_b64":"q71oezTXnIs8umSOfLaiToskPxo0E8tdat2QpuCDLBv6jcaxj4h+BSlHJ2x056zJFe1v9BwPHJ3P5nMvoDnUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9f865b88fd84385a60b1e58d1c32f30977b7112850f8798d92c413047d75f47","last_reissued_at":"2026-07-05T11:27:39.783406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:39.783406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Calvin Murdock, Dinesh Manocha, Ishwarya Ananthabhotla, Ruohan Gao, Sanjoy Chowdhury, Sayan Nag, Subrata Biswas, Tushar Nagarajan, Vamsi Krishna Ithapu, Yijun Qian","submitted_at":"2025-06-26T08:09:16Z","abstract_excerpt":"Modern perception models, particularly those designed for multisensory egocentric tasks, have achieved remarkable performance but often come with substantial computational costs. These high demands pose challenges for real-world deployment, especially in resource-constrained environments. In this paper, we introduce EgoAdapt, a framework that adaptively performs cross-modal distillation and policy learning to enable efficient inference across different egocentric perception tasks, including egocentric action recognition, active speaker localization, and behavior anticipation. Our proposed poli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21080","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/2506.21080/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":"2506.21080","created_at":"2026-07-05T11:27:39.783460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21080v1","created_at":"2026-07-05T11:27:39.783460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21080","created_at":"2026-07-05T11:27:39.783460+00:00"},{"alias_kind":"pith_short_12","alias_value":"XH4GLOEP3BBY","created_at":"2026-07-05T11:27:39.783460+00:00"},{"alias_kind":"pith_short_16","alias_value":"XH4GLOEP3BBYLJQL","created_at":"2026-07-05T11:27:39.783460+00:00"},{"alias_kind":"pith_short_8","alias_value":"XH4GLOEP","created_at":"2026-07-05T11:27:39.783460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07470","citing_title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC","json":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC.json","graph_json":"https://pith.science/api/pith-number/XH4GLOEP3BBYLJQLDZMNDQZPGC/graph.json","events_json":"https://pith.science/api/pith-number/XH4GLOEP3BBYLJQLDZMNDQZPGC/events.json","paper":"https://pith.science/paper/XH4GLOEP"},"agent_actions":{"view_html":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC","download_json":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC.json","view_paper":"https://pith.science/paper/XH4GLOEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21080&json=true","fetch_graph":"https://pith.science/api/pith-number/XH4GLOEP3BBYLJQLDZMNDQZPGC/graph.json","fetch_events":"https://pith.science/api/pith-number/XH4GLOEP3BBYLJQLDZMNDQZPGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC/action/storage_attestation","attest_author":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC/action/author_attestation","sign_citation":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC/action/citation_signature","submit_replication":"https://pith.science/pith/XH4GLOEP3BBYLJQLDZMNDQZPGC/action/replication_record"}},"created_at":"2026-07-05T11:27:39.783460+00:00","updated_at":"2026-07-05T11:27:39.783460+00:00"}