{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BSG2OSBZMMAPPFFUKZGPFVBMWC","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":"b6e6dde2dabe8b199ebfcd58f81dcb229cf723440cc548c39cef017ef9492d34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T10:29:08Z","title_canon_sha256":"cf7b429a714994f383177ccf6fb7632a3208bcdc6eac7e5091016c287799c373"},"schema_version":"1.0","source":{"id":"2503.13026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13026","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13026v2","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13026","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_12","alias_value":"BSG2OSBZMMAP","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_16","alias_value":"BSG2OSBZMMAPPFFU","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_8","alias_value":"BSG2OSBZ","created_at":"2026-07-05T11:38:05Z"}],"graph_snapshots":[{"event_id":"sha256:11eb9d73ec3a251f1cfddd1e59630b52f1e80ab6ed157e52cb9ac2c5bf890d8c","target":"graph","created_at":"2026-07-05T11:38:05Z","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/2503.13026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable performance of large multimodal models (LMMs) has attracted significant interest from the image segmentation community. To align with the next-token-prediction paradigm, current LMM-driven segmentation methods either use object boundary points to represent masks or introduce special segmentation tokens, whose hidden states are decoded by a segmentation model requiring the original image as input. However, these approaches often suffer from inadequate mask representation and complex architectures, limiting the potential of LMMs. In this work, we propose the Hierarchical Mask Toke","authors_text":"Changxu Cheng, Lingfeng Wang, Senda Chen, Tao Wang, Wuyue Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T10:29:08Z","title":"HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13026","kind":"arxiv","version":2},"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":"sha256:35a685a6a689c2f43269e267db49f2cf1e3296522a7b62de80c2b2bdca15c7fa","target":"record","created_at":"2026-07-05T11:38:05Z","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":"b6e6dde2dabe8b199ebfcd58f81dcb229cf723440cc548c39cef017ef9492d34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T10:29:08Z","title_canon_sha256":"cf7b429a714994f383177ccf6fb7632a3208bcdc6eac7e5091016c287799c373"},"schema_version":"1.0","source":{"id":"2503.13026","kind":"arxiv","version":2}},"canonical_sha256":"0c8da748396300f794b4564cf2d42cb09dfd8e0602b0124550f9cd0d12d94dee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c8da748396300f794b4564cf2d42cb09dfd8e0602b0124550f9cd0d12d94dee","first_computed_at":"2026-07-05T11:38:05.597609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:05.597609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0y3j1KEaMc7iUQ5iAGf2YoFzmHPs+jV+q8nH5cOB82XYAZzN2B4dcawE3TA5lJXyuNYy749r06VPGWzGPv1UBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:05.598108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35a685a6a689c2f43269e267db49f2cf1e3296522a7b62de80c2b2bdca15c7fa","sha256:11eb9d73ec3a251f1cfddd1e59630b52f1e80ab6ed157e52cb9ac2c5bf890d8c"],"state_sha256":"06bbe7428efb1386725178792a9baf7d8373af5792e0fcd0ba1c091b10bbf041"}