{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PTBULQEI5OQOK5VX6DEWXDHGHA","short_pith_number":"pith:PTBULQEI","canonical_record":{"source":{"id":"2409.19960","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:24:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"eb7ae04c60c6c1cd2fb484e99a3f78ab0f2611dd62f7e122b8dd459702ba4175","abstract_canon_sha256":"8a6fcf3ab28cd4340a6e9fc9e43ec6e1b3bba5389b97c15187b5f1cb87c4b20c"},"schema_version":"1.0"},"canonical_sha256":"7cc345c088eba0e576b7f0c96b8ce6383990f9e23e6233ab75797a9faea1adb7","source":{"kind":"arxiv","id":"2409.19960","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19960","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19960v2","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19960","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"pith_short_12","alias_value":"PTBULQEI5OQO","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"pith_short_16","alias_value":"PTBULQEI5OQOK5VX","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"pith_short_8","alias_value":"PTBULQEI","created_at":"2026-07-05T09:30:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PTBULQEI5OQOK5VX6DEWXDHGHA","target":"record","payload":{"canonical_record":{"source":{"id":"2409.19960","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:24:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"eb7ae04c60c6c1cd2fb484e99a3f78ab0f2611dd62f7e122b8dd459702ba4175","abstract_canon_sha256":"8a6fcf3ab28cd4340a6e9fc9e43ec6e1b3bba5389b97c15187b5f1cb87c4b20c"},"schema_version":"1.0"},"canonical_sha256":"7cc345c088eba0e576b7f0c96b8ce6383990f9e23e6233ab75797a9faea1adb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:21.649938Z","signature_b64":"r/46zkykND32xOEAvR1KjrnQsvWHirU/ddyeCwZgwlIO9j9Ou9BqtcJ/bln45U4NjrAJ7BkZDuBAGMI0dMABCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cc345c088eba0e576b7f0c96b8ce6383990f9e23e6233ab75797a9faea1adb7","last_reissued_at":"2026-07-05T09:30:21.649523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:21.649523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.19960","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23azds0tNtSv7ptOhpz/f++rknsBgnKAHGLUEaEN8DQKLkdFWXJ/528bMQJb1OqGHXKWy08wIF+M37Ett+zZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:28:35.040630Z"},"content_sha256":"d166426c9ac4919263dbb6d65afd2cc9b0e5f53e1d266879e44e896c32748fdf","schema_version":"1.0","event_id":"sha256:d166426c9ac4919263dbb6d65afd2cc9b0e5f53e1d266879e44e896c32748fdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PTBULQEI5OQOK5VX6DEWXDHGHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Joshua Feinglass, Yezhou Yang","submitted_at":"2024-09-30T05:24:01Z","abstract_excerpt":"Zero-shot inference, where pre-trained models perform tasks without specific training data, is an exciting emergent ability of large models like CLIP. Although there has been considerable exploration into enhancing zero-shot abilities in image captioning (IC) for popular datasets such as MSCOCO and Flickr8k, these approaches fall short with fine-grained datasets like CUB, FLO, UCM-Captions, and Sydney-Captions. These datasets require captions to discern between visually and semantically similar classes, focusing on detailed object parts and their attributes. To overcome this challenge, we intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19960","kind":"arxiv","version":2},"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/2409.19960/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":"2026-07-05T09:30:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1YtntBj25/AvjfJufJ5H+WCTqt6KuCHcdfY2hPXRwV+SYYFT+fQ+CuLB0FpmApRzxp4IGEZLyXxMrYL6I6FkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:28:35.041146Z"},"content_sha256":"dacec029bc53269e4d24a35326dfe2f327343f295340c18b41e770467e9409d6","schema_version":"1.0","event_id":"sha256:dacec029bc53269e4d24a35326dfe2f327343f295340c18b41e770467e9409d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTBULQEI5OQOK5VX6DEWXDHGHA/bundle.json","state_url":"https://pith.science/pith/PTBULQEI5OQOK5VX6DEWXDHGHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTBULQEI5OQOK5VX6DEWXDHGHA/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":"2026-08-20T12:28:35Z","links":{"resolver":"https://pith.science/pith/PTBULQEI5OQOK5VX6DEWXDHGHA","bundle":"https://pith.science/pith/PTBULQEI5OQOK5VX6DEWXDHGHA/bundle.json","state":"https://pith.science/pith/PTBULQEI5OQOK5VX6DEWXDHGHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTBULQEI5OQOK5VX6DEWXDHGHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PTBULQEI5OQOK5VX6DEWXDHGHA","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":"8a6fcf3ab28cd4340a6e9fc9e43ec6e1b3bba5389b97c15187b5f1cb87c4b20c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:24:01Z","title_canon_sha256":"eb7ae04c60c6c1cd2fb484e99a3f78ab0f2611dd62f7e122b8dd459702ba4175"},"schema_version":"1.0","source":{"id":"2409.19960","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19960","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19960v2","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19960","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"pith_short_12","alias_value":"PTBULQEI5OQO","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"pith_short_16","alias_value":"PTBULQEI5OQOK5VX","created_at":"2026-07-05T09:30:21Z"},{"alias_kind":"pith_short_8","alias_value":"PTBULQEI","created_at":"2026-07-05T09:30:21Z"}],"graph_snapshots":[{"event_id":"sha256:dacec029bc53269e4d24a35326dfe2f327343f295340c18b41e770467e9409d6","target":"graph","created_at":"2026-07-05T09:30:21Z","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/2409.19960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot inference, where pre-trained models perform tasks without specific training data, is an exciting emergent ability of large models like CLIP. Although there has been considerable exploration into enhancing zero-shot abilities in image captioning (IC) for popular datasets such as MSCOCO and Flickr8k, these approaches fall short with fine-grained datasets like CUB, FLO, UCM-Captions, and Sydney-Captions. These datasets require captions to discern between visually and semantically similar classes, focusing on detailed object parts and their attributes. To overcome this challenge, we intr","authors_text":"Joshua Feinglass, Yezhou Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:24:01Z","title":"TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19960","kind":"arxiv","version":2},"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:d166426c9ac4919263dbb6d65afd2cc9b0e5f53e1d266879e44e896c32748fdf","target":"record","created_at":"2026-07-05T09:30:21Z","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":"8a6fcf3ab28cd4340a6e9fc9e43ec6e1b3bba5389b97c15187b5f1cb87c4b20c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:24:01Z","title_canon_sha256":"eb7ae04c60c6c1cd2fb484e99a3f78ab0f2611dd62f7e122b8dd459702ba4175"},"schema_version":"1.0","source":{"id":"2409.19960","kind":"arxiv","version":2}},"canonical_sha256":"7cc345c088eba0e576b7f0c96b8ce6383990f9e23e6233ab75797a9faea1adb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cc345c088eba0e576b7f0c96b8ce6383990f9e23e6233ab75797a9faea1adb7","first_computed_at":"2026-07-05T09:30:21.649523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:21.649523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r/46zkykND32xOEAvR1KjrnQsvWHirU/ddyeCwZgwlIO9j9Ou9BqtcJ/bln45U4NjrAJ7BkZDuBAGMI0dMABCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:21.649938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19960","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d166426c9ac4919263dbb6d65afd2cc9b0e5f53e1d266879e44e896c32748fdf","sha256:dacec029bc53269e4d24a35326dfe2f327343f295340c18b41e770467e9409d6"],"state_sha256":"905222dc25a331bae81236d367e66f583e49ce2c108616211c5a1ee7260a372d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fdTEERldDiRquAot1VJQ0b2IEjhhD+2vDLAPcATiupZtaQEl+6047W6Nbon3PATqbZ7kd6gnMB0FFhhIA/tDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:28:35.046226Z","bundle_sha256":"1906b7f3e9f1eaa375e1ceab90e845d8c1f8bd58e05d7f39dd97d54b4c5bd009"}}