{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VWLJL65675VPTH27TYCCQWNFIR","short_pith_number":"pith:VWLJL656","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"},"canonical_sha256":"ad9695fbbeff6af99f5f9e042859a5446dc257ea895fe217090aa20e03d73ea1","source":{"kind":"arxiv","id":"2606.19341","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19341","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19341v1","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19341","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"VWLJL65675VP","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"VWLJL65675VPTH27","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"VWLJL656","created_at":"2026-06-19T16:12:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VWLJL65675VPTH27TYCCQWNFIR","target":"record","payload":{"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"},"canonical_sha256":"ad9695fbbeff6af99f5f9e042859a5446dc257ea895fe217090aa20e03d73ea1","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"},"source_kind":"arxiv","source_id":"2606.19341","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":"2026-06-19T16:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L2e8WtiJnRDUazTkZMJ92q7t1CKzNmcIKlPBIy8ZBQQrd2KCSfF5LSI5X2pX7AQ9l6MVb/zeqeOEahAveK3GAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T11:46:22.899609Z"},"content_sha256":"e8c92693bcc418d35e9a68104d8492cd9628394140b83531256052e22a9fdf10","schema_version":"1.0","event_id":"sha256:e8c92693bcc418d35e9a68104d8492cd9628394140b83531256052e22a9fdf10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VWLJL65675VPTH27TYCCQWNFIR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mLAVWLRaU0pkkSWBeFNFeMh+IFIaSYPrgDkDbPwhpWHbVBbtnTqA8zWiirg9quPLBnd5LA6GFIQVtb72YsLhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T11:46:22.899995Z"},"content_sha256":"04fc5a368af9cdc259e0da09a0f36b5a96a2281b7ef0f3465ff43c46ba320acc","schema_version":"1.0","event_id":"sha256:04fc5a368af9cdc259e0da09a0f36b5a96a2281b7ef0f3465ff43c46ba320acc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/bundle.json","state_url":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWLJL65675VPTH27TYCCQWNFIR/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":"2026-07-01T11:46:22Z","links":{"resolver":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR","bundle":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/bundle.json","state":"https://pith.science/pith/VWLJL65675VPTH27TYCCQWNFIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWLJL65675VPTH27TYCCQWNFIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VWLJL65675VPTH27TYCCQWNFIR","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":"7308f2bb1b8fe5932ae1d7520f153ad314d58b1a19478d0bb9f9fb2faaa8fd61","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T17:59:56Z","title_canon_sha256":"d2485ab1d7b6ca36bcfdfda002755d618ca7a02bcc179a611df17a2e67821d91"},"schema_version":"1.0","source":{"id":"2606.19341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19341","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19341v1","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19341","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"VWLJL65675VP","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"VWLJL65675VPTH27","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"VWLJL656","created_at":"2026-06-19T16:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:04fc5a368af9cdc259e0da09a0f36b5a96a2281b7ef0f3465ff43c46ba320acc","target":"graph","created_at":"2026-06-19T16:12:11Z","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/2606.19341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T17:59:56Z","title":"Native Active Perception as Reasoning for Omni-Modal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19341","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:e8c92693bcc418d35e9a68104d8492cd9628394140b83531256052e22a9fdf10","target":"record","created_at":"2026-06-19T16:12:11Z","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":"7308f2bb1b8fe5932ae1d7520f153ad314d58b1a19478d0bb9f9fb2faaa8fd61","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T17:59:56Z","title_canon_sha256":"d2485ab1d7b6ca36bcfdfda002755d618ca7a02bcc179a611df17a2e67821d91"},"schema_version":"1.0","source":{"id":"2606.19341","kind":"arxiv","version":1}},"canonical_sha256":"ad9695fbbeff6af99f5f9e042859a5446dc257ea895fe217090aa20e03d73ea1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad9695fbbeff6af99f5f9e042859a5446dc257ea895fe217090aa20e03d73ea1","first_computed_at":"2026-06-19T16:12:11.690700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:11.690700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FG4HuWklhpOShgOxxixtTQnMwQwRPfWEziAtdTZvRUs6vzdRbUL5m2pTnnfG2OCVt/P0q9k32qdCCr4m1Ac+Dg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:11.691077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8c92693bcc418d35e9a68104d8492cd9628394140b83531256052e22a9fdf10","sha256:04fc5a368af9cdc259e0da09a0f36b5a96a2281b7ef0f3465ff43c46ba320acc"],"state_sha256":"f24da688ec447f92fec53e5179864cc7c687ff9d29e04a10a2694af29268e5fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTVH+Bs+aFkDXX1Dfhewn0thwegtHySYfbC5BBfi8w3NJ9+femYq2YVRW/DYRslR4nPI2rwwyuPB4y6FSkbVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T11:46:22.902188Z","bundle_sha256":"28a18441504f5caf25e99633ad85c3403baeb0b8c15b72bccee7f0a4a61abe76"}}