{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LYKBEJU2Q434PI4LT3DTLWKLIY","short_pith_number":"pith:LYKBEJU2","canonical_record":{"source":{"id":"2607.23235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T14:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"89ae38931bb448217b7dc29788ce82f28e98170e3d59c1b297d0f8e0fef2339a","abstract_canon_sha256":"430fd1f5de0936b8d844bf0ebd50104044eae56e32a132ec789c1fb0fd82848d"},"schema_version":"1.0"},"canonical_sha256":"5e1412269a8737c7a38b9ec735d94b460ca92e3c6eb48385570f2e2d48e5de56","source":{"kind":"arxiv","id":"2607.23235","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23235","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23235v1","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23235","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"LYKBEJU2Q434","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"LYKBEJU2Q434PI4L","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"LYKBEJU2","created_at":"2026-07-28T01:22:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LYKBEJU2Q434PI4LT3DTLWKLIY","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T14:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"89ae38931bb448217b7dc29788ce82f28e98170e3d59c1b297d0f8e0fef2339a","abstract_canon_sha256":"430fd1f5de0936b8d844bf0ebd50104044eae56e32a132ec789c1fb0fd82848d"},"schema_version":"1.0"},"canonical_sha256":"5e1412269a8737c7a38b9ec735d94b460ca92e3c6eb48385570f2e2d48e5de56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:43.226949Z","signature_b64":"+4hOLio+HOKiobrb9g39ML2WRen2RVI3lJ8o9x8dd/2E2Eb8xiNlGDfd8/YW07M1nn6vkDvnJqlmewlStAknAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e1412269a8737c7a38b9ec735d94b460ca92e3c6eb48385570f2e2d48e5de56","last_reissued_at":"2026-07-28T01:22:43.226159Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:43.226159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23235","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":"2026-07-28T01:22:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdXCmiIhJHNqUNiS1Z9hcfLE7t2AXGS9Jm3UANGoGmdP/yVOcHADbhEnEkiD4Adm1zNKyRslc4y9Ph2jlDCRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:56:42.873686Z"},"content_sha256":"0d5a053b30463ab3ccc2c6e2480c5411401a1bd4732802fefc1aa70391389bf8","schema_version":"1.0","event_id":"sha256:0d5a053b30463ab3ccc2c6e2480c5411401a1bd4732802fefc1aa70391389bf8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LYKBEJU2Q434PI4LT3DTLWKLIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Reconstruction-Based Framework for Caption Evaluation Beyond Reference Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianqiang Huang, Jiaxin Qi, Kaihua Tang, Yuhua Zheng, Zhijiang Tang","submitted_at":"2026-07-25T14:41:34Z","abstract_excerpt":"Image captioning is a primary task in vision--language research, yet assessing how faithfully a caption preserves image semantics without relying on reference captions remains unsettled. Prevailing evaluations rely on human-annotated references, whose content reflects annotator intent and captioning proficiency. In this paper, we study a reconstruction-based principle for caption evaluation: a caption is as good as its capacity to enable reconstruction of the original image. However, because captioning inherently compresses visual information, it is impossible to recover all details, and pixel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23235","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/2607.23235/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":"2026-07-28T01:22:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mer0XaNl3queKGrP5VGfAjiG0mSNP6klqbD1YuO06v391sUhAsc5mJjiqSBfj3NSJeGvsMdejzsMezl64YIGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:56:42.874219Z"},"content_sha256":"67a262bdd949904b72ef5373652246ba9ee15efc807be11b0d0e5ca138d34d35","schema_version":"1.0","event_id":"sha256:67a262bdd949904b72ef5373652246ba9ee15efc807be11b0d0e5ca138d34d35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/bundle.json","state_url":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/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":"2026-08-03T22:56:42Z","links":{"resolver":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY","bundle":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/bundle.json","state":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LYKBEJU2Q434PI4LT3DTLWKLIY","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":"430fd1f5de0936b8d844bf0ebd50104044eae56e32a132ec789c1fb0fd82848d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T14:41:34Z","title_canon_sha256":"89ae38931bb448217b7dc29788ce82f28e98170e3d59c1b297d0f8e0fef2339a"},"schema_version":"1.0","source":{"id":"2607.23235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23235","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23235v1","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23235","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"LYKBEJU2Q434","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"LYKBEJU2Q434PI4L","created_at":"2026-07-28T01:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"LYKBEJU2","created_at":"2026-07-28T01:22:43Z"}],"graph_snapshots":[{"event_id":"sha256:67a262bdd949904b72ef5373652246ba9ee15efc807be11b0d0e5ca138d34d35","target":"graph","created_at":"2026-07-28T01:22:43Z","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/2607.23235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning is a primary task in vision--language research, yet assessing how faithfully a caption preserves image semantics without relying on reference captions remains unsettled. Prevailing evaluations rely on human-annotated references, whose content reflects annotator intent and captioning proficiency. In this paper, we study a reconstruction-based principle for caption evaluation: a caption is as good as its capacity to enable reconstruction of the original image. However, because captioning inherently compresses visual information, it is impossible to recover all details, and pixel","authors_text":"Jianqiang Huang, Jiaxin Qi, Kaihua Tang, Yuhua Zheng, Zhijiang Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T14:41:34Z","title":"A Reconstruction-Based Framework for Caption Evaluation Beyond Reference Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23235","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":"sha256:0d5a053b30463ab3ccc2c6e2480c5411401a1bd4732802fefc1aa70391389bf8","target":"record","created_at":"2026-07-28T01:22:43Z","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":"430fd1f5de0936b8d844bf0ebd50104044eae56e32a132ec789c1fb0fd82848d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T14:41:34Z","title_canon_sha256":"89ae38931bb448217b7dc29788ce82f28e98170e3d59c1b297d0f8e0fef2339a"},"schema_version":"1.0","source":{"id":"2607.23235","kind":"arxiv","version":1}},"canonical_sha256":"5e1412269a8737c7a38b9ec735d94b460ca92e3c6eb48385570f2e2d48e5de56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e1412269a8737c7a38b9ec735d94b460ca92e3c6eb48385570f2e2d48e5de56","first_computed_at":"2026-07-28T01:22:43.226159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:43.226159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+4hOLio+HOKiobrb9g39ML2WRen2RVI3lJ8o9x8dd/2E2Eb8xiNlGDfd8/YW07M1nn6vkDvnJqlmewlStAknAw==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:43.226949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d5a053b30463ab3ccc2c6e2480c5411401a1bd4732802fefc1aa70391389bf8","sha256:67a262bdd949904b72ef5373652246ba9ee15efc807be11b0d0e5ca138d34d35"],"state_sha256":"34f5d621ccf48679697370c6e011a76dca3631f29e2cc975cc344e127b68c075"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2wWsEmwdoZ2hBYUkearMgzoSye7mFpvrHDpO0vw87uZ0VmZ9MT0aoeyrCC/mhUNAiiIuFqtgmzwkn+7MwH3tBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:56:42.878335Z","bundle_sha256":"045181454c7e51b8cfe0fa5f017afb5f489130b2461b613fc8bf47b2da6714dd"}}