{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OICW5K4Q5IMPOWRWF45BO2CHNY","short_pith_number":"pith:OICW5K4Q","schema_version":"1.0","canonical_sha256":"72056eab90ea18f75a362f3a1768476e287753b25bfa860d7a11663fbf097d45","source":{"kind":"arxiv","id":"2607.24098","version":1},"attestation_state":"computed","paper":{"title":"ReflexTrack: A Feedback-Driven Agent for Training-Free Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Josef Kittler, Tao Zhou, Tianyang Xu, Xiao-Jun Wu, Yuanjia Li, Zhangyong Tang","submitted_at":"2026-07-27T07:39:20Z","abstract_excerpt":"Referring video object segmentation (RVOS) requires segmenting a target specified by natural language throughout a video. Recent agentic approaches combine multimodal large language models with promptable segmentation models to perform RVOS without task-specific training. However, most pipelines rely on one-shot spatial grounding followed by mask propagation, leaving both the initial prompts and temporal predictions largely unverified. We introduce ReflexTrack, a training-free, feedback-driven agent that closes this loop at both spatial and temporal levels. Mask-guided Spatial Refinement evalu"},"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":"2607.24098","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T07:39:20Z","cross_cats_sorted":[],"title_canon_sha256":"13509a55809a78c37bcef5ef6883c83b3c667fd6dd8b851bd9f2e301cad040a2","abstract_canon_sha256":"bcd3c2f88c0b9820c13199e0a937d00991a45517be52539729aa5217397a770c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:45.064004Z","signature_b64":"crlb0tl2K68qceEAsjLTcQsSe6qGoKcpdkZgjE0TDte4zlme9O7x8MzLoz1JrSnW9ICmj3W2tfmJ8y3F0vE5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72056eab90ea18f75a362f3a1768476e287753b25bfa860d7a11663fbf097d45","last_reissued_at":"2026-07-28T01:23:45.063157Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:45.063157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReflexTrack: A Feedback-Driven Agent for Training-Free Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Josef Kittler, Tao Zhou, Tianyang Xu, Xiao-Jun Wu, Yuanjia Li, Zhangyong Tang","submitted_at":"2026-07-27T07:39:20Z","abstract_excerpt":"Referring video object segmentation (RVOS) requires segmenting a target specified by natural language throughout a video. Recent agentic approaches combine multimodal large language models with promptable segmentation models to perform RVOS without task-specific training. However, most pipelines rely on one-shot spatial grounding followed by mask propagation, leaving both the initial prompts and temporal predictions largely unverified. We introduce ReflexTrack, a training-free, feedback-driven agent that closes this loop at both spatial and temporal levels. Mask-guided Spatial Refinement evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24098","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/2607.24098/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":"2607.24098","created_at":"2026-07-28T01:23:45.063601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24098v1","created_at":"2026-07-28T01:23:45.063601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24098","created_at":"2026-07-28T01:23:45.063601+00:00"},{"alias_kind":"pith_short_12","alias_value":"OICW5K4Q5IMP","created_at":"2026-07-28T01:23:45.063601+00:00"},{"alias_kind":"pith_short_16","alias_value":"OICW5K4Q5IMPOWRW","created_at":"2026-07-28T01:23:45.063601+00:00"},{"alias_kind":"pith_short_8","alias_value":"OICW5K4Q","created_at":"2026-07-28T01:23:45.063601+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/OICW5K4Q5IMPOWRWF45BO2CHNY","json":"https://pith.science/pith/OICW5K4Q5IMPOWRWF45BO2CHNY.json","graph_json":"https://pith.science/api/pith-number/OICW5K4Q5IMPOWRWF45BO2CHNY/graph.json","events_json":"https://pith.science/api/pith-number/OICW5K4Q5IMPOWRWF45BO2CHNY/events.json","paper":"https://pith.science/paper/OICW5K4Q"},"agent_actions":{"view_html":"https://pith.science/pith/OICW5K4Q5IMPOWRWF45BO2CHNY","download_json":"https://pith.science/pith/OICW5K4Q5IMPOWRWF45BO2CHNY.json","view_paper":"https://pith.science/paper/OICW5K4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24098&json=true","fetch_graph":"https://pith.science/api/pith-number/OICW5K4Q5IMPOWRWF45BO2CHNY/graph.json","fetch_events":"https://pith.science/api/pith-number/OICW5K4Q5IMPOWRWF45BO2CHNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OICW5K4Q5IMPOWRWF45BO2CHNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OICW5K4Q5IMPOWRWF45BO2CHNY/action/storage_attestation","attest_author":"https://pith.science/pith/OICW5K4Q5IMPOWRWF45BO2CHNY/action/author_attestation","sign_citation":"https://pith.science/pith/OICW5K4Q5IMPOWRWF45BO2CHNY/action/citation_signature","submit_replication":"https://pith.science/pith/OICW5K4Q5IMPOWRWF45BO2CHNY/action/replication_record"}},"created_at":"2026-07-28T01:23:45.063601+00:00","updated_at":"2026-07-28T01:23:45.063601+00:00"}