{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VWLJL65675VPTH27TYCCQWNFIR","short_pith_number":"pith:VWLJL656","schema_version":"1.0","canonical_sha256":"ad9695fbbeff6af99f5f9e042859a5446dc257ea895fe217090aa20e03d73ea1","source":{"kind":"arxiv","id":"2606.19341","version":1},"attestation_state":"computed","paper":{"title":"Native Active Perception as Reasoning for Omni-Modal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Jin Xu, Jinzheng He, Junyang Lin, Pheng-Ann Heng, Qize Yang, Ruiyang Xu, Yunfei Chu, Yuxuan Wang, Zhenghao Xing, Ziyang Ma","submitted_at":"2026-06-17T17:59:56Z","abstract_excerpt":"Passive models for long video understanding typically rely on a \"watch-it-all\" paradigm, processing frames uniformly regardless of query difficulty, causing computational cost to grow with video duration. Although interactive frameworks have emerged, they often rely on global pre-scanning, and their context cost still scales with video length. We propose OmniAgent, the first native omni-modal agent that formulates video understanding as a POMDP-based iterative Observation-Thought-Action cycle. OmniAgent executes on-demand actions to selectively distill audio-visual cues into a persistent textu"},"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":"2606.19341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T17:59:56Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"d2485ab1d7b6ca36bcfdfda002755d618ca7a02bcc179a611df17a2e67821d91","abstract_canon_sha256":"7308f2bb1b8fe5932ae1d7520f153ad314d58b1a19478d0bb9f9fb2faaa8fd61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:11.691077Z","signature_b64":"FG4HuWklhpOShgOxxixtTQnMwQwRPfWEziAtdTZvRUs6vzdRbUL5m2pTnnfG2OCVt/P0q9k32qdCCr4m1Ac+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad9695fbbeff6af99f5f9e042859a5446dc257ea895fe217090aa20e03d73ea1","last_reissued_at":"2026-06-19T16:12:11.690700Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:11.690700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Native Active Perception as Reasoning for Omni-Modal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Jin Xu, Jinzheng He, Junyang Lin, Pheng-Ann Heng, Qize Yang, Ruiyang Xu, Yunfei Chu, Yuxuan Wang, Zhenghao Xing, Ziyang Ma","submitted_at":"2026-06-17T17:59:56Z","abstract_excerpt":"Passive models for long video understanding typically rely on a \"watch-it-all\" paradigm, processing frames uniformly regardless of query difficulty, causing computational cost to grow with video duration. Although interactive frameworks have emerged, they often rely on global pre-scanning, and their context cost still scales with video length. We propose OmniAgent, the first native omni-modal agent that formulates video understanding as a POMDP-based iterative Observation-Thought-Action cycle. OmniAgent executes on-demand actions to selectively distill audio-visual cues into a persistent textu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19341","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/2606.19341/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":"2606.19341","created_at":"2026-06-19T16:12:11.690765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19341v1","created_at":"2026-06-19T16:12:11.690765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19341","created_at":"2026-06-19T16:12:11.690765+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWLJL65675VP","created_at":"2026-06-19T16:12:11.690765+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWLJL65675VPTH27","created_at":"2026-06-19T16:12:11.690765+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWLJL656","created_at":"2026-06-19T16:12:11.690765+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/VWLJL65675VPTH27TYCCQWNFIR","json":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR.json","graph_json":"https://pith.science/api/pith-number/VWLJL65675VPTH27TYCCQWNFIR/graph.json","events_json":"https://pith.science/api/pith-number/VWLJL65675VPTH27TYCCQWNFIR/events.json","paper":"https://pith.science/paper/VWLJL656"},"agent_actions":{"view_html":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR","download_json":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR.json","view_paper":"https://pith.science/paper/VWLJL656","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19341&json=true","fetch_graph":"https://pith.science/api/pith-number/VWLJL65675VPTH27TYCCQWNFIR/graph.json","fetch_events":"https://pith.science/api/pith-number/VWLJL65675VPTH27TYCCQWNFIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/action/storage_attestation","attest_author":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/action/author_attestation","sign_citation":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/action/citation_signature","submit_replication":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/action/replication_record"}},"created_at":"2026-06-19T16:12:11.690765+00:00","updated_at":"2026-06-19T16:12:11.690765+00:00"}