{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TBSGGXHFYTRM2ML45IOTZGV4W4","short_pith_number":"pith:TBSGGXHF","canonical_record":{"source":{"id":"2307.16686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T14:00:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dfc59f48fc7e6b0d048a7ba989d993c2cb7b69e61be2971a3d00837ab9ee6866","abstract_canon_sha256":"28ce5495757587215b62cb895b32746bcfa08c7f01d6b6365ce7d5f8d0ad364a"},"schema_version":"1.0"},"canonical_sha256":"9864635ce5c4e2cd317cea1d3c9abcb7108c69747023e10ddee2c5cf199f796f","source":{"kind":"arxiv","id":"2307.16686","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16686","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16686v1","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16686","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"pith_short_12","alias_value":"TBSGGXHFYTRM","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"pith_short_16","alias_value":"TBSGGXHFYTRM2ML4","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"pith_short_8","alias_value":"TBSGGXHF","created_at":"2026-07-05T06:36:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TBSGGXHFYTRM2ML45IOTZGV4W4","target":"record","payload":{"canonical_record":{"source":{"id":"2307.16686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T14:00:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dfc59f48fc7e6b0d048a7ba989d993c2cb7b69e61be2971a3d00837ab9ee6866","abstract_canon_sha256":"28ce5495757587215b62cb895b32746bcfa08c7f01d6b6365ce7d5f8d0ad364a"},"schema_version":"1.0"},"canonical_sha256":"9864635ce5c4e2cd317cea1d3c9abcb7108c69747023e10ddee2c5cf199f796f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:06.891627Z","signature_b64":"0jDBs+IY1XO8vfvA0IsOqkO04yrkeXwNSMXpp8YI+6e/V6tsZYpryKMG1viCc+H8zwvFI0oNYKXaB6iWVXIGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9864635ce5c4e2cd317cea1d3c9abcb7108c69747023e10ddee2c5cf199f796f","last_reissued_at":"2026-07-05T06:36:06.891235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:06.891235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.16686","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":"2026-07-05T06:36:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vlmp2wjHeapzOk4w+nqy7rLCAtM8x8vpkplp7qLl/+jSf8vR7P8NYKZmYRf9e06C1K3X5StRld4pKqSkH5QXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:43:49.253729Z"},"content_sha256":"4575a02086e1a3c11e052dd0b990704b9edf45099fa921b424a06106e792f6ff","schema_version":"1.0","event_id":"sha256:4575a02086e1a3c11e052dd0b990704b9edf45099fa921b424a06106e792f6ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TBSGGXHFYTRM2ML45IOTZGV4W4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guiding Image Captioning Models Toward More Specific Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lala Li, Simon Kornblith, Thao Nguyen, Zirui Wang","submitted_at":"2023-07-31T14:00:12Z","abstract_excerpt":"Image captioning is conventionally formulated as the task of generating captions for images that match the distribution of reference image-caption pairs. However, reference captions in standard captioning datasets are short and may not uniquely identify the images they describe. These problems are further exacerbated when models are trained directly on image-alt text pairs collected from the internet. In this work, we show that it is possible to generate more specific captions with minimal changes to the training process. We implement classifier-free guidance for an autoregressive captioning m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16686","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/2307.16686/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":"2026-07-05T06:36:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QTOBnq1Y0q8z2E64jeFK8o15yLrCb1my0YUnOrzvNh8sCVm0qKRJaDq8PQu6EKysu8Adg++C0i7qamXqRvNvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:43:49.254138Z"},"content_sha256":"31d98f24832043ccf97c42af14604359923908a3deba47ea6206a3e16dcb3efa","schema_version":"1.0","event_id":"sha256:31d98f24832043ccf97c42af14604359923908a3deba47ea6206a3e16dcb3efa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TBSGGXHFYTRM2ML45IOTZGV4W4/bundle.json","state_url":"https://pith.science/pith/TBSGGXHFYTRM2ML45IOTZGV4W4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TBSGGXHFYTRM2ML45IOTZGV4W4/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":"2026-07-07T02:43:49Z","links":{"resolver":"https://pith.science/pith/TBSGGXHFYTRM2ML45IOTZGV4W4","bundle":"https://pith.science/pith/TBSGGXHFYTRM2ML45IOTZGV4W4/bundle.json","state":"https://pith.science/pith/TBSGGXHFYTRM2ML45IOTZGV4W4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TBSGGXHFYTRM2ML45IOTZGV4W4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TBSGGXHFYTRM2ML45IOTZGV4W4","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":"28ce5495757587215b62cb895b32746bcfa08c7f01d6b6365ce7d5f8d0ad364a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T14:00:12Z","title_canon_sha256":"dfc59f48fc7e6b0d048a7ba989d993c2cb7b69e61be2971a3d00837ab9ee6866"},"schema_version":"1.0","source":{"id":"2307.16686","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16686","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16686v1","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16686","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"pith_short_12","alias_value":"TBSGGXHFYTRM","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"pith_short_16","alias_value":"TBSGGXHFYTRM2ML4","created_at":"2026-07-05T06:36:06Z"},{"alias_kind":"pith_short_8","alias_value":"TBSGGXHF","created_at":"2026-07-05T06:36:06Z"}],"graph_snapshots":[{"event_id":"sha256:31d98f24832043ccf97c42af14604359923908a3deba47ea6206a3e16dcb3efa","target":"graph","created_at":"2026-07-05T06:36:06Z","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/2307.16686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning is conventionally formulated as the task of generating captions for images that match the distribution of reference image-caption pairs. However, reference captions in standard captioning datasets are short and may not uniquely identify the images they describe. These problems are further exacerbated when models are trained directly on image-alt text pairs collected from the internet. In this work, we show that it is possible to generate more specific captions with minimal changes to the training process. We implement classifier-free guidance for an autoregressive captioning m","authors_text":"Lala Li, Simon Kornblith, Thao Nguyen, Zirui Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T14:00:12Z","title":"Guiding Image Captioning Models Toward More Specific Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16686","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":"sha256:4575a02086e1a3c11e052dd0b990704b9edf45099fa921b424a06106e792f6ff","target":"record","created_at":"2026-07-05T06:36:06Z","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":"28ce5495757587215b62cb895b32746bcfa08c7f01d6b6365ce7d5f8d0ad364a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T14:00:12Z","title_canon_sha256":"dfc59f48fc7e6b0d048a7ba989d993c2cb7b69e61be2971a3d00837ab9ee6866"},"schema_version":"1.0","source":{"id":"2307.16686","kind":"arxiv","version":1}},"canonical_sha256":"9864635ce5c4e2cd317cea1d3c9abcb7108c69747023e10ddee2c5cf199f796f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9864635ce5c4e2cd317cea1d3c9abcb7108c69747023e10ddee2c5cf199f796f","first_computed_at":"2026-07-05T06:36:06.891235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:06.891235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0jDBs+IY1XO8vfvA0IsOqkO04yrkeXwNSMXpp8YI+6e/V6tsZYpryKMG1viCc+H8zwvFI0oNYKXaB6iWVXIGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:06.891627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16686","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4575a02086e1a3c11e052dd0b990704b9edf45099fa921b424a06106e792f6ff","sha256:31d98f24832043ccf97c42af14604359923908a3deba47ea6206a3e16dcb3efa"],"state_sha256":"4122ff987aca9950716ae083478b42e59e68368a5ff8ad992ff8a560388766be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iWMdbCMhXDjPWqt9rcTwuieQjsAVIT0KhsSItuyzSEP+j55pA+nBmp5FtKuWtqmk+nOQQI94WY7o+JkcfnP4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:43:49.256149Z","bundle_sha256":"fee1c2253345835133beae1ab9ed8ebb82917577ed89d706ba72731ec3161da1"}}