{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RLFJOOXGJVKPHRZVMNWQJ33JXF","short_pith_number":"pith:RLFJOOXG","schema_version":"1.0","canonical_sha256":"8aca973ae64d54f3c735636d04ef69b951469912ae9f01c07800e3745ae14b08","source":{"kind":"arxiv","id":"2410.18923","version":2},"attestation_state":"computed","paper":{"title":"SegLLM: Multi-round Reasoning Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kazuki Kozuka, Kehan Li, Konstantinos Kallidromitis, Shaolun Zhang, Shufan Li, Trevor Darrell, Xudong Wang, Yusuke Kato","submitted_at":"2024-10-24T17:11:52Z","abstract_excerpt":"We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual outputs. By leveraging a mask-aware multimodal LLM, SegLLM re-integrates previous segmentation results into its input stream, enabling it to reason about complex user intentions and segment objects in relation to previously identified entities, including positional, interactional, and hierarchical relationships, across multiple interactions. This capability allows SegLLM to respond to visual and text queries in a cha"},"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":"2410.18923","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T17:11:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"421fcc4189c57490712dcf963247e4e7c023a6e7bcda22d9a324e61733c8c21c","abstract_canon_sha256":"47269ebf649ffc3726a17bedeb6fcea8e724aead8df1afe6fbb48c0754002d45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:34.621276Z","signature_b64":"kiBm7HuAMoX234F0PrPDMtNTW280doy/KAJQkN6xtNPkf47601RXsgibVSMjZZYx01ZY398F18Nu+rP21xeQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aca973ae64d54f3c735636d04ef69b951469912ae9f01c07800e3745ae14b08","last_reissued_at":"2026-07-05T09:29:34.619855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:34.619855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegLLM: Multi-round Reasoning Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kazuki Kozuka, Kehan Li, Konstantinos Kallidromitis, Shaolun Zhang, Shufan Li, Trevor Darrell, Xudong Wang, Yusuke Kato","submitted_at":"2024-10-24T17:11:52Z","abstract_excerpt":"We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual outputs. By leveraging a mask-aware multimodal LLM, SegLLM re-integrates previous segmentation results into its input stream, enabling it to reason about complex user intentions and segment objects in relation to previously identified entities, including positional, interactional, and hierarchical relationships, across multiple interactions. This capability allows SegLLM to respond to visual and text queries in a cha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18923","kind":"arxiv","version":2},"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/2410.18923/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":"2410.18923","created_at":"2026-07-05T09:29:34.620707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18923v2","created_at":"2026-07-05T09:29:34.620707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18923","created_at":"2026-07-05T09:29:34.620707+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLFJOOXGJVKP","created_at":"2026-07-05T09:29:34.620707+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLFJOOXGJVKPHRZV","created_at":"2026-07-05T09:29:34.620707+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLFJOOXG","created_at":"2026-07-05T09:29:34.620707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00987","citing_title":"An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23500","citing_title":"B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23500","citing_title":"B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22068","citing_title":"COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":177,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF","json":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF.json","graph_json":"https://pith.science/api/pith-number/RLFJOOXGJVKPHRZVMNWQJ33JXF/graph.json","events_json":"https://pith.science/api/pith-number/RLFJOOXGJVKPHRZVMNWQJ33JXF/events.json","paper":"https://pith.science/paper/RLFJOOXG"},"agent_actions":{"view_html":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF","download_json":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF.json","view_paper":"https://pith.science/paper/RLFJOOXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18923&json=true","fetch_graph":"https://pith.science/api/pith-number/RLFJOOXGJVKPHRZVMNWQJ33JXF/graph.json","fetch_events":"https://pith.science/api/pith-number/RLFJOOXGJVKPHRZVMNWQJ33JXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF/action/storage_attestation","attest_author":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF/action/author_attestation","sign_citation":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF/action/citation_signature","submit_replication":"https://pith.science/pith/RLFJOOXGJVKPHRZVMNWQJ33JXF/action/replication_record"}},"created_at":"2026-07-05T09:29:34.620707+00:00","updated_at":"2026-07-05T09:29:34.620707+00:00"}