{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TQ2TOG72KAFB5QI3464XDS2GMF","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":"2c935fbd526f5748571535e5319072a6322154ed0b3f7d78ec57530ad69d08ab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T18:55:20Z","title_canon_sha256":"3686b214cd2ceb7ba1dc4d309e574a298e294c28a4e5bc61da46a1ccad68bcd0"},"schema_version":"1.0","source":{"id":"2301.02229","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02229","created_at":"2026-07-05T05:41:38Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02229v2","created_at":"2026-07-05T05:41:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02229","created_at":"2026-07-05T05:41:38Z"},{"alias_kind":"pith_short_12","alias_value":"TQ2TOG72KAFB","created_at":"2026-07-05T05:41:38Z"},{"alias_kind":"pith_short_16","alias_value":"TQ2TOG72KAFB5QI3","created_at":"2026-07-05T05:41:38Z"},{"alias_kind":"pith_short_8","alias_value":"TQ2TOG72","created_at":"2026-07-05T05:41:38Z"}],"graph_snapshots":[{"event_id":"sha256:8e9e0a25f96632d950fcbe8fb18e57e799bcc4cd30252c140196691af34f6be6","target":"graph","created_at":"2026-07-05T05:41:38Z","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/2301.02229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike language tasks, where the output space is usually limited to a set of tokens, the output space of visual tasks is more complicated, making it difficult to build a unified visual model for various visual tasks. In this paper, we seek to unify the output space of visual tasks, so that we can also build a unified model for visual tasks. To this end, we demonstrate a single unified model that simultaneously handles two typical visual tasks of instance segmentation and depth estimation, which have discrete/fixed-length and continuous/varied-length outputs, respectively. We propose several ne","authors_text":"Chen Li, Han Hu, Jia Ning, Kun He, Qi Dai, Zheng Zhang, Zigang Geng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T18:55:20Z","title":"All in Tokens: Unifying Output Space of Visual Tasks via Soft Token"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02229","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":"sha256:8dbec55dc04e4b6667b5a260ad4468b76ef74e4ee5d83e58460472689342abb9","target":"record","created_at":"2026-07-05T05:41:38Z","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":"2c935fbd526f5748571535e5319072a6322154ed0b3f7d78ec57530ad69d08ab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T18:55:20Z","title_canon_sha256":"3686b214cd2ceb7ba1dc4d309e574a298e294c28a4e5bc61da46a1ccad68bcd0"},"schema_version":"1.0","source":{"id":"2301.02229","kind":"arxiv","version":2}},"canonical_sha256":"9c35371bfa500a1ec11be7b971cb46617656b8b0a06d783b9f82b6a185c6c9c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c35371bfa500a1ec11be7b971cb46617656b8b0a06d783b9f82b6a185c6c9c8","first_computed_at":"2026-07-05T05:41:38.815278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:41:38.815278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SUp2aoIVKgDVlbyALWY9BKo2keKs3ULd8to/pkmo0PWhuJVHZI41hkA5xx2PtbdNam/JY7gtGt8IG8m8XLkOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:41:38.815721Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.02229","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dbec55dc04e4b6667b5a260ad4468b76ef74e4ee5d83e58460472689342abb9","sha256:8e9e0a25f96632d950fcbe8fb18e57e799bcc4cd30252c140196691af34f6be6"],"state_sha256":"61e0323377b6277d6053c544faa1d1dd0f459ebc1fbf996dfef4ce8cd8055061"}