{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CJNWN5X3VBJKCGMSXDQFF2GVPK","short_pith_number":"pith:CJNWN5X3","schema_version":"1.0","canonical_sha256":"125b66f6fba852a11992b8e052e8d57ab849d8151949dddbd78b49b42bfb6d4a","source":{"kind":"arxiv","id":"2312.09128","version":2},"attestation_state":"computed","paper":{"title":"Tokenize Anything via Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lulu Tang, Shiguang Shan, Ting Pan, Xinlong Wang","submitted_at":"2023-12-14T17:01:02Z","abstract_excerpt":"We present a unified, promptable model capable of simultaneously segmenting, recognizing, and captioning anything. Unlike SAM, we aim to build a versatile region representation in the wild via visual prompting. To achieve this, we train a generalizable model with massive segmentation masks, \\eg, SA-1B masks, and semantic priors from a pre-trained CLIP model with 5 billion parameters. Specifically, we construct a promptable image decoder by adding a semantic token to each mask token. The semantic token is responsible for learning the semantic priors in a predefined concept space. Through joint "},"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":"2312.09128","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T17:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"ff885e966ef1fa910a082c7b0b2fc483774f27a7acac291c88c63964af78316b","abstract_canon_sha256":"33834b8a90ea94db31bd7bc5a7bd6294e9817419bf794869b1e02d825cc97dce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:49.997370Z","signature_b64":"S1Fg5Aln8Pdsi/0D7py8YJb/ofXH3pmNb2+Y4LQTXh02pDMQneA56ncYNM+DmLvvWiEPzmeSxM7AjcC/m1pTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"125b66f6fba852a11992b8e052e8d57ab849d8151949dddbd78b49b42bfb6d4a","last_reissued_at":"2026-07-05T08:44:49.996942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:49.996942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tokenize Anything via Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lulu Tang, Shiguang Shan, Ting Pan, Xinlong Wang","submitted_at":"2023-12-14T17:01:02Z","abstract_excerpt":"We present a unified, promptable model capable of simultaneously segmenting, recognizing, and captioning anything. Unlike SAM, we aim to build a versatile region representation in the wild via visual prompting. To achieve this, we train a generalizable model with massive segmentation masks, \\eg, SA-1B masks, and semantic priors from a pre-trained CLIP model with 5 billion parameters. Specifically, we construct a promptable image decoder by adding a semantic token to each mask token. The semantic token is responsible for learning the semantic priors in a predefined concept space. Through joint "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09128","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/2312.09128/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":"2312.09128","created_at":"2026-07-05T08:44:49.997000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09128v2","created_at":"2026-07-05T08:44:49.997000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09128","created_at":"2026-07-05T08:44:49.997000+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJNWN5X3VBJK","created_at":"2026-07-05T08:44:49.997000+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJNWN5X3VBJKCGMS","created_at":"2026-07-05T08:44:49.997000+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJNWN5X3","created_at":"2026-07-05T08:44:49.997000+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/CJNWN5X3VBJKCGMSXDQFF2GVPK","json":"https://pith.science/pith/CJNWN5X3VBJKCGMSXDQFF2GVPK.json","graph_json":"https://pith.science/api/pith-number/CJNWN5X3VBJKCGMSXDQFF2GVPK/graph.json","events_json":"https://pith.science/api/pith-number/CJNWN5X3VBJKCGMSXDQFF2GVPK/events.json","paper":"https://pith.science/paper/CJNWN5X3"},"agent_actions":{"view_html":"https://pith.science/pith/CJNWN5X3VBJKCGMSXDQFF2GVPK","download_json":"https://pith.science/pith/CJNWN5X3VBJKCGMSXDQFF2GVPK.json","view_paper":"https://pith.science/paper/CJNWN5X3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09128&json=true","fetch_graph":"https://pith.science/api/pith-number/CJNWN5X3VBJKCGMSXDQFF2GVPK/graph.json","fetch_events":"https://pith.science/api/pith-number/CJNWN5X3VBJKCGMSXDQFF2GVPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJNWN5X3VBJKCGMSXDQFF2GVPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJNWN5X3VBJKCGMSXDQFF2GVPK/action/storage_attestation","attest_author":"https://pith.science/pith/CJNWN5X3VBJKCGMSXDQFF2GVPK/action/author_attestation","sign_citation":"https://pith.science/pith/CJNWN5X3VBJKCGMSXDQFF2GVPK/action/citation_signature","submit_replication":"https://pith.science/pith/CJNWN5X3VBJKCGMSXDQFF2GVPK/action/replication_record"}},"created_at":"2026-07-05T08:44:49.997000+00:00","updated_at":"2026-07-05T08:44:49.997000+00:00"}