{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6RZ4ZTRAV537QREUU64KLZEI7E","short_pith_number":"pith:6RZ4ZTRA","schema_version":"1.0","canonical_sha256":"f473ccce20af77f84494a7b8a5e488f9037958e00199535d1dcfd742a9f46a4f","source":{"kind":"arxiv","id":"2311.18835","version":1},"attestation_state":"computed","paper":{"title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tian, Hongsheng Li, Jifeng Dai, Jingqiu Zhou, Rongyao Fang, Shilin Yan, Zhaoyang Huang","submitted_at":"2023-11-30T18:59:51Z","abstract_excerpt":"Empowering models to dynamically accomplish tasks specified through natural language instructions represents a promising path toward more capable and general artificial intelligence. In this work, we introduce InstructSeq, an instruction-conditioned multi-modal modeling framework that unifies diverse vision tasks through flexible natural language control and handling of both visual and textual data. InstructSeq employs a multimodal transformer architecture encompassing visual, language, and sequential modeling. We utilize a visual encoder to extract image features and a text encoder to encode "},"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":"2311.18835","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"bb006a289357645b7bc7224f127ad0459dcfe43dd3be8b3bc05f2c4334b59179","abstract_canon_sha256":"55e9154fca56402e5ed8227b8a1183bbf5057e2fd2fa2c4bbf2243dd817970ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:47.360139Z","signature_b64":"lFaC2J5Qy0sQWmaVclerjLr5EkccCmbZqhuyryIo0d19opwsYt29zNweQHSESeAoRBa4kLByGccsdjv1Bw+NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f473ccce20af77f84494a7b8a5e488f9037958e00199535d1dcfd742a9f46a4f","last_reissued_at":"2026-07-05T07:18:47.359651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:47.359651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tian, Hongsheng Li, Jifeng Dai, Jingqiu Zhou, Rongyao Fang, Shilin Yan, Zhaoyang Huang","submitted_at":"2023-11-30T18:59:51Z","abstract_excerpt":"Empowering models to dynamically accomplish tasks specified through natural language instructions represents a promising path toward more capable and general artificial intelligence. In this work, we introduce InstructSeq, an instruction-conditioned multi-modal modeling framework that unifies diverse vision tasks through flexible natural language control and handling of both visual and textual data. InstructSeq employs a multimodal transformer architecture encompassing visual, language, and sequential modeling. We utilize a visual encoder to extract image features and a text encoder to encode "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18835","kind":"arxiv","version":1},"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/2311.18835/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":"2311.18835","created_at":"2026-07-05T07:18:47.359709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18835v1","created_at":"2026-07-05T07:18:47.359709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18835","created_at":"2026-07-05T07:18:47.359709+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RZ4ZTRAV537","created_at":"2026-07-05T07:18:47.359709+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RZ4ZTRAV537QREU","created_at":"2026-07-05T07:18:47.359709+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RZ4ZTRA","created_at":"2026-07-05T07:18:47.359709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.04326","citing_title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E","json":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E.json","graph_json":"https://pith.science/api/pith-number/6RZ4ZTRAV537QREUU64KLZEI7E/graph.json","events_json":"https://pith.science/api/pith-number/6RZ4ZTRAV537QREUU64KLZEI7E/events.json","paper":"https://pith.science/paper/6RZ4ZTRA"},"agent_actions":{"view_html":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E","download_json":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E.json","view_paper":"https://pith.science/paper/6RZ4ZTRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18835&json=true","fetch_graph":"https://pith.science/api/pith-number/6RZ4ZTRAV537QREUU64KLZEI7E/graph.json","fetch_events":"https://pith.science/api/pith-number/6RZ4ZTRAV537QREUU64KLZEI7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E/action/storage_attestation","attest_author":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E/action/author_attestation","sign_citation":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E/action/citation_signature","submit_replication":"https://pith.science/pith/6RZ4ZTRAV537QREUU64KLZEI7E/action/replication_record"}},"created_at":"2026-07-05T07:18:47.359709+00:00","updated_at":"2026-07-05T07:18:47.359709+00:00"}