{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TQ2TOG72KAFB5QI3464XDS2GMF","short_pith_number":"pith:TQ2TOG72","schema_version":"1.0","canonical_sha256":"9c35371bfa500a1ec11be7b971cb46617656b8b0a06d783b9f82b6a185c6c9c8","source":{"kind":"arxiv","id":"2301.02229","version":2},"attestation_state":"computed","paper":{"title":"All in Tokens: Unifying Output Space of Visual Tasks via Soft Token","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Li, Han Hu, Jia Ning, Kun He, Qi Dai, Zheng Zhang, Zigang Geng","submitted_at":"2023-01-05T18:55:20Z","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"},"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":"2301.02229","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T18:55:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3686b214cd2ceb7ba1dc4d309e574a298e294c28a4e5bc61da46a1ccad68bcd0","abstract_canon_sha256":"2c935fbd526f5748571535e5319072a6322154ed0b3f7d78ec57530ad69d08ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:38.815721Z","signature_b64":"SUp2aoIVKgDVlbyALWY9BKo2keKs3ULd8to/pkmo0PWhuJVHZI41hkA5xx2PtbdNam/JY7gtGt8IG8m8XLkOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c35371bfa500a1ec11be7b971cb46617656b8b0a06d783b9f82b6a185c6c9c8","last_reissued_at":"2026-07-05T05:41:38.815278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:38.815278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"All in Tokens: Unifying Output Space of Visual Tasks via Soft Token","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Li, Han Hu, Jia Ning, Kun He, Qi Dai, Zheng Zhang, Zigang Geng","submitted_at":"2023-01-05T18:55:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02229","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/2301.02229/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":"2301.02229","created_at":"2026-07-05T05:41:38.815340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02229v2","created_at":"2026-07-05T05:41:38.815340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02229","created_at":"2026-07-05T05:41:38.815340+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQ2TOG72KAFB","created_at":"2026-07-05T05:41:38.815340+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQ2TOG72KAFB5QI3","created_at":"2026-07-05T05:41:38.815340+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQ2TOG72","created_at":"2026-07-05T05:41:38.815340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02881","citing_title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07726","citing_title":"PaliGemma: A versatile 3B VLM for transfer","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02881","citing_title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF","json":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF.json","graph_json":"https://pith.science/api/pith-number/TQ2TOG72KAFB5QI3464XDS2GMF/graph.json","events_json":"https://pith.science/api/pith-number/TQ2TOG72KAFB5QI3464XDS2GMF/events.json","paper":"https://pith.science/paper/TQ2TOG72"},"agent_actions":{"view_html":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF","download_json":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF.json","view_paper":"https://pith.science/paper/TQ2TOG72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02229&json=true","fetch_graph":"https://pith.science/api/pith-number/TQ2TOG72KAFB5QI3464XDS2GMF/graph.json","fetch_events":"https://pith.science/api/pith-number/TQ2TOG72KAFB5QI3464XDS2GMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF/action/storage_attestation","attest_author":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF/action/author_attestation","sign_citation":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF/action/citation_signature","submit_replication":"https://pith.science/pith/TQ2TOG72KAFB5QI3464XDS2GMF/action/replication_record"}},"created_at":"2026-07-05T05:41:38.815340+00:00","updated_at":"2026-07-05T05:41:38.815340+00:00"}