{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:UNYUTF7L3PR2NH37ESFQSEVNFS","short_pith_number":"pith:UNYUTF7L","canonical_record":{"source":{"id":"1604.03249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T05:23:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bf203dedd5053039aef8b83ac88511fb31799f08e18135ebece6d0547de4f123","abstract_canon_sha256":"394628551f8eef57267682138ce5e0e43d9ea1c3a30fa82e6fa4ed000c0564aa"},"schema_version":"1.0"},"canonical_sha256":"a3714997ebdbe3a69f7f248b0912ad2c840b8a9bcab123d00e6eae023a322641","source":{"kind":"arxiv","id":"1604.03249","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.03249","created_at":"2026-05-18T01:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"1604.03249v1","created_at":"2026-05-18T01:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03249","created_at":"2026-05-18T01:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"UNYUTF7L3PR2","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UNYUTF7L3PR2NH37","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UNYUTF7L","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:UNYUTF7L3PR2NH37ESFQSEVNFS","target":"record","payload":{"canonical_record":{"source":{"id":"1604.03249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T05:23:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bf203dedd5053039aef8b83ac88511fb31799f08e18135ebece6d0547de4f123","abstract_canon_sha256":"394628551f8eef57267682138ce5e0e43d9ea1c3a30fa82e6fa4ed000c0564aa"},"schema_version":"1.0"},"canonical_sha256":"a3714997ebdbe3a69f7f248b0912ad2c840b8a9bcab123d00e6eae023a322641","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:15.912677Z","signature_b64":"v25C0FOIaZpjX1osuqELONNrHwgbaEfQGLpp95kUCHRz8wjMSrRK0soS5zC6dFIfWNG4xDXnL7GELOh5lN2FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3714997ebdbe3a69f7f248b0912ad2c840b8a9bcab123d00e6eae023a322641","last_reissued_at":"2026-05-18T01:17:15.911945Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:15.911945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.03249","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":"2026-05-18T01:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nRZnbncn0dS/4hfgBLo90od0xVpd+IQPgLczBVlh/LhKXFW627pFKCtWehfawhT/POmb9uEXB0xa/UzxYzDABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:25:21.246553Z"},"content_sha256":"e8722c7d53db124ee3cb6269800b08643126ac1c81cea2b4be31af3ab955ab91","schema_version":"1.0","event_id":"sha256:e8722c7d53db124ee3cb6269800b08643126ac1c81cea2b4be31af3ab955ab91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:UNYUTF7L3PR2NH37ESFQSEVNFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attributes as Semantic Units between Natural Language and Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Marcus Rohrbach","submitted_at":"2016-04-12T05:23:26Z","abstract_excerpt":"Impressive progress has been made in the fields of computer vision and natural language processing. However, it remains a challenge to find the best point of interaction for these very different modalities. In this chapter we discuss how attributes allow us to exchange information between the two modalities and in this way lead to an interaction on a semantic level. Specifically we discuss how attributes allow using knowledge mined from language resources for recognizing novel visual categories, how we can generate sentence description about images and video, how we can ground natural language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03249","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":""},"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":"2026-05-18T01:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNFkn8UPiJKeXdsEZ1divPGl/Kr1tZBBIpaHpg30RwSqOLm5nX+rGxAZqRoXV2fk169ZYbrPn/hvOWkhlxRnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:25:21.246905Z"},"content_sha256":"2fcdea6ec7205f76d9bfbe8a181bf1ce39313a0de71a8d4a8ea9013a9b452da1","schema_version":"1.0","event_id":"sha256:2fcdea6ec7205f76d9bfbe8a181bf1ce39313a0de71a8d4a8ea9013a9b452da1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNYUTF7L3PR2NH37ESFQSEVNFS/bundle.json","state_url":"https://pith.science/pith/UNYUTF7L3PR2NH37ESFQSEVNFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNYUTF7L3PR2NH37ESFQSEVNFS/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":"2026-05-19T11:25:21Z","links":{"resolver":"https://pith.science/pith/UNYUTF7L3PR2NH37ESFQSEVNFS","bundle":"https://pith.science/pith/UNYUTF7L3PR2NH37ESFQSEVNFS/bundle.json","state":"https://pith.science/pith/UNYUTF7L3PR2NH37ESFQSEVNFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNYUTF7L3PR2NH37ESFQSEVNFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:UNYUTF7L3PR2NH37ESFQSEVNFS","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":"394628551f8eef57267682138ce5e0e43d9ea1c3a30fa82e6fa4ed000c0564aa","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T05:23:26Z","title_canon_sha256":"bf203dedd5053039aef8b83ac88511fb31799f08e18135ebece6d0547de4f123"},"schema_version":"1.0","source":{"id":"1604.03249","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.03249","created_at":"2026-05-18T01:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"1604.03249v1","created_at":"2026-05-18T01:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03249","created_at":"2026-05-18T01:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"UNYUTF7L3PR2","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UNYUTF7L3PR2NH37","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UNYUTF7L","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:2fcdea6ec7205f76d9bfbe8a181bf1ce39313a0de71a8d4a8ea9013a9b452da1","target":"graph","created_at":"2026-05-18T01:17:15Z","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"},"paper":{"abstract_excerpt":"Impressive progress has been made in the fields of computer vision and natural language processing. However, it remains a challenge to find the best point of interaction for these very different modalities. In this chapter we discuss how attributes allow us to exchange information between the two modalities and in this way lead to an interaction on a semantic level. Specifically we discuss how attributes allow using knowledge mined from language resources for recognizing novel visual categories, how we can generate sentence description about images and video, how we can ground natural language","authors_text":"Marcus Rohrbach","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T05:23:26Z","title":"Attributes as Semantic Units between Natural Language and Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03249","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:e8722c7d53db124ee3cb6269800b08643126ac1c81cea2b4be31af3ab955ab91","target":"record","created_at":"2026-05-18T01:17:15Z","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":"394628551f8eef57267682138ce5e0e43d9ea1c3a30fa82e6fa4ed000c0564aa","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-12T05:23:26Z","title_canon_sha256":"bf203dedd5053039aef8b83ac88511fb31799f08e18135ebece6d0547de4f123"},"schema_version":"1.0","source":{"id":"1604.03249","kind":"arxiv","version":1}},"canonical_sha256":"a3714997ebdbe3a69f7f248b0912ad2c840b8a9bcab123d00e6eae023a322641","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3714997ebdbe3a69f7f248b0912ad2c840b8a9bcab123d00e6eae023a322641","first_computed_at":"2026-05-18T01:17:15.911945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:15.911945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v25C0FOIaZpjX1osuqELONNrHwgbaEfQGLpp95kUCHRz8wjMSrRK0soS5zC6dFIfWNG4xDXnL7GELOh5lN2FDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:15.912677Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.03249","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8722c7d53db124ee3cb6269800b08643126ac1c81cea2b4be31af3ab955ab91","sha256:2fcdea6ec7205f76d9bfbe8a181bf1ce39313a0de71a8d4a8ea9013a9b452da1"],"state_sha256":"10d3eb4a8cec1e2a271135a0f9c73aafb5cb563a1f9c42c8f27fadc0eee806dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bae6KGMTXjbnaorAeXnKrZDSi+yrDUnoH4pZKfN5MV7MxsFJInl9qBvk9sVbLgCwwkzVWRIDyEjuDnAJnHmpBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T11:25:21.248579Z","bundle_sha256":"3fa8e4787344b8dad270911d276bce7e0ce57f85bb14bc46515d2d5c31f1b216"}}