{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GJEONPOHIGNVE7CWHQ6EPGEJN6","short_pith_number":"pith:GJEONPOH","canonical_record":{"source":{"id":"2310.00031","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T05:16:41Z","cross_cats_sorted":[],"title_canon_sha256":"dec8142055233a1877dc697525285dc834b58157accdc7158f5cc112de28bee9","abstract_canon_sha256":"424d622bcc99b57d7adc3a49820d5eb42070bd039f53ab54032f46222122828f"},"schema_version":"1.0"},"canonical_sha256":"3248e6bdc7419b527c563c3c4798896fb50f929d2db443704af1e2976f9f21fc","source":{"kind":"arxiv","id":"2310.00031","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00031","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00031v3","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00031","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"GJEONPOHIGNV","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"pith_short_16","alias_value":"GJEONPOHIGNVE7CW","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"pith_short_8","alias_value":"GJEONPOH","created_at":"2026-07-05T08:02:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GJEONPOHIGNVE7CWHQ6EPGEJN6","target":"record","payload":{"canonical_record":{"source":{"id":"2310.00031","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T05:16:41Z","cross_cats_sorted":[],"title_canon_sha256":"dec8142055233a1877dc697525285dc834b58157accdc7158f5cc112de28bee9","abstract_canon_sha256":"424d622bcc99b57d7adc3a49820d5eb42070bd039f53ab54032f46222122828f"},"schema_version":"1.0"},"canonical_sha256":"3248e6bdc7419b527c563c3c4798896fb50f929d2db443704af1e2976f9f21fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:46.582629Z","signature_b64":"l0tpihnDaDfdgNSWJE+rBLRXYs06azmFN739nLV63GcG0TnpKu7NN12ujHSkNlZC3UnU0VIMXWCAt008GdwlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3248e6bdc7419b527c563c3c4798896fb50f929d2db443704af1e2976f9f21fc","last_reissued_at":"2026-07-05T08:02:46.582117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:46.582117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.00031","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:02:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zsz/u/YVGGfkxVh1kyjVT/7i9VsKDTFXXc5aRVtXAxeGJz/HjkfWvmb8aOAw+ecrdaADBfnjRgP3KlQo4xNJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:03:34.463734Z"},"content_sha256":"140895ecf02923a744e42b1cf11b975d99ccdcee95b33c34ff3924fdff766b61","schema_version":"1.0","event_id":"sha256:140895ecf02923a744e42b1cf11b975d99ccdcee95b33c34ff3924fdff766b61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GJEONPOHIGNVE7CWHQ6EPGEJN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-image Alignment for Diffusion-based Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Manuel Knott, Markus Marks, Neehar Kondapaneni, Pietro Perona, Rogerio Guimaraes","submitted_at":"2023-09-29T05:16:41Z","abstract_excerpt":"Diffusion models are generative models with impressive text-to-image synthesis capabilities and have spurred a new wave of creative methods for classical machine learning tasks. However, the best way to harness the perceptual knowledge of these generative models for visual tasks is still an open question. Specifically, it is unclear how to use the prompting interface when applying diffusion backbones to vision tasks. We find that automatically generated captions can improve text-image alignment and significantly enhance a model's cross-attention maps, leading to better perceptual performance. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00031","kind":"arxiv","version":3},"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/2310.00031/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":"2026-07-05T08:02:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/pKl6QkT+5q/U0EID9frvnoIP8OIo7j4Z28P9PYM98m0kg8us1ogC36jRclfoixt2hj+d1mhtWAWHvUnhXiGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:03:34.464223Z"},"content_sha256":"6d6432aa8ed2285c883fc51eb71e943a7e0c21ca4d5d28369d90b38d60e8cb75","schema_version":"1.0","event_id":"sha256:6d6432aa8ed2285c883fc51eb71e943a7e0c21ca4d5d28369d90b38d60e8cb75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJEONPOHIGNVE7CWHQ6EPGEJN6/bundle.json","state_url":"https://pith.science/pith/GJEONPOHIGNVE7CWHQ6EPGEJN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJEONPOHIGNVE7CWHQ6EPGEJN6/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":"2026-08-06T23:03:34Z","links":{"resolver":"https://pith.science/pith/GJEONPOHIGNVE7CWHQ6EPGEJN6","bundle":"https://pith.science/pith/GJEONPOHIGNVE7CWHQ6EPGEJN6/bundle.json","state":"https://pith.science/pith/GJEONPOHIGNVE7CWHQ6EPGEJN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJEONPOHIGNVE7CWHQ6EPGEJN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GJEONPOHIGNVE7CWHQ6EPGEJN6","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":"424d622bcc99b57d7adc3a49820d5eb42070bd039f53ab54032f46222122828f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T05:16:41Z","title_canon_sha256":"dec8142055233a1877dc697525285dc834b58157accdc7158f5cc112de28bee9"},"schema_version":"1.0","source":{"id":"2310.00031","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00031","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00031v3","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00031","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"GJEONPOHIGNV","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"pith_short_16","alias_value":"GJEONPOHIGNVE7CW","created_at":"2026-07-05T08:02:46Z"},{"alias_kind":"pith_short_8","alias_value":"GJEONPOH","created_at":"2026-07-05T08:02:46Z"}],"graph_snapshots":[{"event_id":"sha256:6d6432aa8ed2285c883fc51eb71e943a7e0c21ca4d5d28369d90b38d60e8cb75","target":"graph","created_at":"2026-07-05T08:02:46Z","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/2310.00031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models are generative models with impressive text-to-image synthesis capabilities and have spurred a new wave of creative methods for classical machine learning tasks. However, the best way to harness the perceptual knowledge of these generative models for visual tasks is still an open question. Specifically, it is unclear how to use the prompting interface when applying diffusion backbones to vision tasks. We find that automatically generated captions can improve text-image alignment and significantly enhance a model's cross-attention maps, leading to better perceptual performance. ","authors_text":"Manuel Knott, Markus Marks, Neehar Kondapaneni, Pietro Perona, Rogerio Guimaraes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T05:16:41Z","title":"Text-image Alignment for Diffusion-based Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00031","kind":"arxiv","version":3},"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":"sha256:140895ecf02923a744e42b1cf11b975d99ccdcee95b33c34ff3924fdff766b61","target":"record","created_at":"2026-07-05T08:02:46Z","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":"424d622bcc99b57d7adc3a49820d5eb42070bd039f53ab54032f46222122828f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T05:16:41Z","title_canon_sha256":"dec8142055233a1877dc697525285dc834b58157accdc7158f5cc112de28bee9"},"schema_version":"1.0","source":{"id":"2310.00031","kind":"arxiv","version":3}},"canonical_sha256":"3248e6bdc7419b527c563c3c4798896fb50f929d2db443704af1e2976f9f21fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3248e6bdc7419b527c563c3c4798896fb50f929d2db443704af1e2976f9f21fc","first_computed_at":"2026-07-05T08:02:46.582117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:46.582117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l0tpihnDaDfdgNSWJE+rBLRXYs06azmFN739nLV63GcG0TnpKu7NN12ujHSkNlZC3UnU0VIMXWCAt008GdwlAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:46.582629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00031","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:140895ecf02923a744e42b1cf11b975d99ccdcee95b33c34ff3924fdff766b61","sha256:6d6432aa8ed2285c883fc51eb71e943a7e0c21ca4d5d28369d90b38d60e8cb75"],"state_sha256":"e493cea515150fe2d869b05e1581a0e919bfe2cbc763e81b78214fe897380692"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H8EGzAXIY5hmHzCkHQO5HSpabE/zUuGbnHIyQ7hLH1JVA91Hcmw9hpfd95NUL4bMywdfYHt/gtDVCcYBemuCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T23:03:34.468667Z","bundle_sha256":"de4e589cbbfa086498f97a4f8bdabb68de06842f139eba41b3afcb8e286bf5c8"}}