{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6RZ4ZTRAV537QREUU64KLZEI7E","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":"55e9154fca56402e5ed8227b8a1183bbf5057e2fd2fa2c4bbf2243dd817970ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:51Z","title_canon_sha256":"bb006a289357645b7bc7224f127ad0459dcfe43dd3be8b3bc05f2c4334b59179"},"schema_version":"1.0","source":{"id":"2311.18835","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18835","created_at":"2026-07-05T07:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18835v1","created_at":"2026-07-05T07:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18835","created_at":"2026-07-05T07:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"6RZ4ZTRAV537","created_at":"2026-07-05T07:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"6RZ4ZTRAV537QREU","created_at":"2026-07-05T07:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"6RZ4ZTRA","created_at":"2026-07-05T07:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:ea3245c83ce83a2186103be69270d7d223d293aa1dfac70f824bfc970811bb02","target":"graph","created_at":"2026-07-05T07:18:47Z","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/2311.18835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Hao Tian, Hongsheng Li, Jifeng Dai, Jingqiu Zhou, Rongyao Fang, Shilin Yan, Zhaoyang Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:51Z","title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18835","kind":"arxiv","version":1},"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":"sha256:2420b4ae1618f8a4c0a83026cedab4430f26f159e72acf56fb4c95bac277b895","target":"record","created_at":"2026-07-05T07:18:47Z","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":"55e9154fca56402e5ed8227b8a1183bbf5057e2fd2fa2c4bbf2243dd817970ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:51Z","title_canon_sha256":"bb006a289357645b7bc7224f127ad0459dcfe43dd3be8b3bc05f2c4334b59179"},"schema_version":"1.0","source":{"id":"2311.18835","kind":"arxiv","version":1}},"canonical_sha256":"f473ccce20af77f84494a7b8a5e488f9037958e00199535d1dcfd742a9f46a4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f473ccce20af77f84494a7b8a5e488f9037958e00199535d1dcfd742a9f46a4f","first_computed_at":"2026-07-05T07:18:47.359651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:47.359651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lFaC2J5Qy0sQWmaVclerjLr5EkccCmbZqhuyryIo0d19opwsYt29zNweQHSESeAoRBa4kLByGccsdjv1Bw+NCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:47.360139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18835","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2420b4ae1618f8a4c0a83026cedab4430f26f159e72acf56fb4c95bac277b895","sha256:ea3245c83ce83a2186103be69270d7d223d293aa1dfac70f824bfc970811bb02"],"state_sha256":"95a49100c740c5e964f80f11b99717c4412bc1a6d4cfdc670b2701687f8ce78a"}