{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BQXYX4JBA5BGJ3VM7WDS4VAJNX","short_pith_number":"pith:BQXYX4JB","canonical_record":{"source":{"id":"2309.03895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T17:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"137b9e8c6f17d8c9706580e3a351e7cba4f5ab0c0f820b40c9ec52ef519cfa1d","abstract_canon_sha256":"c89fd91738cc37e0a8aa738fcc3558dacf02a8d39cb878949a944b0cfa1e65b9"},"schema_version":"1.0"},"canonical_sha256":"0c2f8bf121074264eeacfd872e54096defb8cf5bdcb0da7875dc5fae351cc389","source":{"kind":"arxiv","id":"2309.03895","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.03895","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"2309.03895v1","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03895","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"BQXYX4JBA5BG","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"BQXYX4JBA5BGJ3VM","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"BQXYX4JB","created_at":"2026-07-05T06:48:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BQXYX4JBA5BGJ3VM7WDS4VAJNX","target":"record","payload":{"canonical_record":{"source":{"id":"2309.03895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T17:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"137b9e8c6f17d8c9706580e3a351e7cba4f5ab0c0f820b40c9ec52ef519cfa1d","abstract_canon_sha256":"c89fd91738cc37e0a8aa738fcc3558dacf02a8d39cb878949a944b0cfa1e65b9"},"schema_version":"1.0"},"canonical_sha256":"0c2f8bf121074264eeacfd872e54096defb8cf5bdcb0da7875dc5fae351cc389","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:43.332140Z","signature_b64":"irwHMEDDZV5vg9vIUDSRlxq95dZpGcahz0CqQm/R8NebN5y/hPm4x/qPXu91wNC/2JzBV+LZC+87zKbsxpP+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c2f8bf121074264eeacfd872e54096defb8cf5bdcb0da7875dc5fae351cc389","last_reissued_at":"2026-07-05T06:48:43.331476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:43.331476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.03895","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:48:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eH2kRnHuHs45W8jbsSErfNqgtDlXW+LEaR2dBNLnfxsPwaPLkn9+R1a2cDTRn8jWSkf5tz8SxKsxvje/4Zl6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:50:55.497424Z"},"content_sha256":"ae0468a6da4ae876c213c0fb874b446adeab8868d97f9c0271b7beb596ef5015","schema_version":"1.0","event_id":"sha256:ae0468a6da4ae876c213c0fb874b446adeab8868d97f9c0271b7beb596ef5015"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BQXYX4JBA5BGJ3VM7WDS4VAJNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Binxin Yang, Chen Li, Dong Chen, Han Hu, Jianmin Bao, Shuyang Gu, Tiankai Hang, Ting Zhang, Zheng Zhang, Zigang Geng","submitted_at":"2023-09-07T17:56:57Z","abstract_excerpt":"We present InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions. Unlike existing approaches that integrate prior knowledge and pre-define the output space (e.g., categories and coordinates) for each vision task, we cast diverse vision tasks into a human-intuitive image-manipulating process whose output space is a flexible and interactive pixel space. Concretely, the model is built upon the diffusion process and is trained to predict pixels according to user instructions, such as encircling the man's left shoulder in red or applying a bl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03895","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/2309.03895/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:48:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6Chr2Y4e4eC40eRzpfEdbuD9SwHk4htnAyzVC5R3mat9ifWkidT2fgdkGS3xJFnxObxFcoVRXeVbbQKQnwWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:50:55.497929Z"},"content_sha256":"29704e1e847e0e3c3294e9ba2959fa774f4dd9f0995b26003e4b7faeb689bcb9","schema_version":"1.0","event_id":"sha256:29704e1e847e0e3c3294e9ba2959fa774f4dd9f0995b26003e4b7faeb689bcb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BQXYX4JBA5BGJ3VM7WDS4VAJNX/bundle.json","state_url":"https://pith.science/pith/BQXYX4JBA5BGJ3VM7WDS4VAJNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BQXYX4JBA5BGJ3VM7WDS4VAJNX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T00:50:55Z","links":{"resolver":"https://pith.science/pith/BQXYX4JBA5BGJ3VM7WDS4VAJNX","bundle":"https://pith.science/pith/BQXYX4JBA5BGJ3VM7WDS4VAJNX/bundle.json","state":"https://pith.science/pith/BQXYX4JBA5BGJ3VM7WDS4VAJNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BQXYX4JBA5BGJ3VM7WDS4VAJNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BQXYX4JBA5BGJ3VM7WDS4VAJNX","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":"c89fd91738cc37e0a8aa738fcc3558dacf02a8d39cb878949a944b0cfa1e65b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T17:56:57Z","title_canon_sha256":"137b9e8c6f17d8c9706580e3a351e7cba4f5ab0c0f820b40c9ec52ef519cfa1d"},"schema_version":"1.0","source":{"id":"2309.03895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.03895","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"2309.03895v1","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03895","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"BQXYX4JBA5BG","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"BQXYX4JBA5BGJ3VM","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"BQXYX4JB","created_at":"2026-07-05T06:48:43Z"}],"graph_snapshots":[{"event_id":"sha256:29704e1e847e0e3c3294e9ba2959fa774f4dd9f0995b26003e4b7faeb689bcb9","target":"graph","created_at":"2026-07-05T06:48:43Z","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/2309.03895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions. Unlike existing approaches that integrate prior knowledge and pre-define the output space (e.g., categories and coordinates) for each vision task, we cast diverse vision tasks into a human-intuitive image-manipulating process whose output space is a flexible and interactive pixel space. Concretely, the model is built upon the diffusion process and is trained to predict pixels according to user instructions, such as encircling the man's left shoulder in red or applying a bl","authors_text":"Baining Guo, Binxin Yang, Chen Li, Dong Chen, Han Hu, Jianmin Bao, Shuyang Gu, Tiankai Hang, Ting Zhang, Zheng Zhang, Zigang Geng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T17:56:57Z","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03895","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:ae0468a6da4ae876c213c0fb874b446adeab8868d97f9c0271b7beb596ef5015","target":"record","created_at":"2026-07-05T06:48:43Z","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":"c89fd91738cc37e0a8aa738fcc3558dacf02a8d39cb878949a944b0cfa1e65b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T17:56:57Z","title_canon_sha256":"137b9e8c6f17d8c9706580e3a351e7cba4f5ab0c0f820b40c9ec52ef519cfa1d"},"schema_version":"1.0","source":{"id":"2309.03895","kind":"arxiv","version":1}},"canonical_sha256":"0c2f8bf121074264eeacfd872e54096defb8cf5bdcb0da7875dc5fae351cc389","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c2f8bf121074264eeacfd872e54096defb8cf5bdcb0da7875dc5fae351cc389","first_computed_at":"2026-07-05T06:48:43.331476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:43.331476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"irwHMEDDZV5vg9vIUDSRlxq95dZpGcahz0CqQm/R8NebN5y/hPm4x/qPXu91wNC/2JzBV+LZC+87zKbsxpP+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:43.332140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.03895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae0468a6da4ae876c213c0fb874b446adeab8868d97f9c0271b7beb596ef5015","sha256:29704e1e847e0e3c3294e9ba2959fa774f4dd9f0995b26003e4b7faeb689bcb9"],"state_sha256":"ddc0c87712291b32dd2036e13afd7437e88354aa9334d472650a2c96ba6cb3b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2CEEYnl0Xf5x+l+auUvYSy5sLk4PraB9ErlZWTLA0kOuDjCqP5LCmgjgSpn2IlwiruzmLPHsif9RV52+gcDEBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:50:55.503258Z","bundle_sha256":"f38335efe28ac9db63e29ce349c7e8b9868e79d3361a2c0b14193b0ca9e3f847"}}