{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OXT23RBEMNZC4DCQU2MMLOHLRH","short_pith_number":"pith:OXT23RBE","canonical_record":{"source":{"id":"2506.19848","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d869ebb27eb8c1c069a78fc293a20423a3026b95d269bc534dfd2d9170fce9ed","abstract_canon_sha256":"1b280141c562fd5dfd40ce775595bf20868c876cc08983b4a31c4a0cf6bc0087"},"schema_version":"1.0"},"canonical_sha256":"75e7adc42463722e0c50a698c5b8eb89f4936579671beaac6de686adf4a0fb94","source":{"kind":"arxiv","id":"2506.19848","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19848","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19848v1","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19848","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"OXT23RBEMNZC","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"OXT23RBEMNZC4DCQ","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"OXT23RBE","created_at":"2026-07-05T11:26:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OXT23RBEMNZC4DCQU2MMLOHLRH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.19848","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d869ebb27eb8c1c069a78fc293a20423a3026b95d269bc534dfd2d9170fce9ed","abstract_canon_sha256":"1b280141c562fd5dfd40ce775595bf20868c876cc08983b4a31c4a0cf6bc0087"},"schema_version":"1.0"},"canonical_sha256":"75e7adc42463722e0c50a698c5b8eb89f4936579671beaac6de686adf4a0fb94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:39.512898Z","signature_b64":"yxIRn/Q6diO4rY7hDI2WkTQ2vnbRyTA7qwUOJ7rdBUptov/4rqG1ZjdZja3d1A6iDRE3WtH1S2luyTPL1lnaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75e7adc42463722e0c50a698c5b8eb89f4936579671beaac6de686adf4a0fb94","last_reissued_at":"2026-07-05T11:26:39.512416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:39.512416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.19848","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":"2026-07-05T11:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oi7M7maUtZJXjrQJdnpCtYPJUzQBQ0DC3qSEiBI2n7jNRBVj/7VMFE+m/4gpFZKYyntm/OCg20a1pg9CXbPSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:09:46.219373Z"},"content_sha256":"e1f89cc53fd6f2b1d79d28d699a64936624db220552f87c6c6dd967c6652a9fe","schema_version":"1.0","event_id":"sha256:e1f89cc53fd6f2b1d79d28d699a64936624db220552f87c6c6dd967c6652a9fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OXT23RBEMNZC4DCQU2MMLOHLRH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Feng Wu, Jiaqi Wang, Jinsong Li, Long Xing, Nenghai Yu, Pan Zhang, Qidong Huang, Shuangrui Ding, Weiming Zhang, Xiaoyi Dong, Yuhang Cao, Yuhang Zang","submitted_at":"2025-06-24T17:59:55Z","abstract_excerpt":"This paper presents ScaleCap, an inference-time scalable image captioning strategy that generates comprehensive and detailed image captions. The key challenges of high-quality image captioning lie in the inherent biases of LVLMs: multimodal bias resulting in imbalanced descriptive granularity, offering detailed accounts of some elements while merely skimming over others; linguistic bias leading to hallucinated descriptions of non-existent objects. To address these issues, we propose a scalable debiased captioning strategy, which continuously enriches and calibrates the caption with increased i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19848","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/2506.19848/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":"2026-07-05T11:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x3RGbKyu1DozLkl70P7BBrRmIgsqkRwLE68H6Hu7VWamCrLMp63yYDivk8sVSkHTQsCZlRgU0b7rWKAe2o2LBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:09:46.219935Z"},"content_sha256":"79deead5e90a6cdd5b89a6a61eb9323ce627f0384e4de1c45d00a723c53919b7","schema_version":"1.0","event_id":"sha256:79deead5e90a6cdd5b89a6a61eb9323ce627f0384e4de1c45d00a723c53919b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXT23RBEMNZC4DCQU2MMLOHLRH/bundle.json","state_url":"https://pith.science/pith/OXT23RBEMNZC4DCQU2MMLOHLRH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXT23RBEMNZC4DCQU2MMLOHLRH/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":"2026-08-03T09:09:46Z","links":{"resolver":"https://pith.science/pith/OXT23RBEMNZC4DCQU2MMLOHLRH","bundle":"https://pith.science/pith/OXT23RBEMNZC4DCQU2MMLOHLRH/bundle.json","state":"https://pith.science/pith/OXT23RBEMNZC4DCQU2MMLOHLRH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXT23RBEMNZC4DCQU2MMLOHLRH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OXT23RBEMNZC4DCQU2MMLOHLRH","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":"1b280141c562fd5dfd40ce775595bf20868c876cc08983b4a31c4a0cf6bc0087","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:55Z","title_canon_sha256":"d869ebb27eb8c1c069a78fc293a20423a3026b95d269bc534dfd2d9170fce9ed"},"schema_version":"1.0","source":{"id":"2506.19848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19848","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19848v1","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19848","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"OXT23RBEMNZC","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"OXT23RBEMNZC4DCQ","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"OXT23RBE","created_at":"2026-07-05T11:26:39Z"}],"graph_snapshots":[{"event_id":"sha256:79deead5e90a6cdd5b89a6a61eb9323ce627f0384e4de1c45d00a723c53919b7","target":"graph","created_at":"2026-07-05T11:26:39Z","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/2506.19848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents ScaleCap, an inference-time scalable image captioning strategy that generates comprehensive and detailed image captions. The key challenges of high-quality image captioning lie in the inherent biases of LVLMs: multimodal bias resulting in imbalanced descriptive granularity, offering detailed accounts of some elements while merely skimming over others; linguistic bias leading to hallucinated descriptions of non-existent objects. To address these issues, we propose a scalable debiased captioning strategy, which continuously enriches and calibrates the caption with increased i","authors_text":"Dahua Lin, Feng Wu, Jiaqi Wang, Jinsong Li, Long Xing, Nenghai Yu, Pan Zhang, Qidong Huang, Shuangrui Ding, Weiming Zhang, Xiaoyi Dong, Yuhang Cao, Yuhang Zang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:55Z","title":"ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19848","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:e1f89cc53fd6f2b1d79d28d699a64936624db220552f87c6c6dd967c6652a9fe","target":"record","created_at":"2026-07-05T11:26:39Z","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":"1b280141c562fd5dfd40ce775595bf20868c876cc08983b4a31c4a0cf6bc0087","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:55Z","title_canon_sha256":"d869ebb27eb8c1c069a78fc293a20423a3026b95d269bc534dfd2d9170fce9ed"},"schema_version":"1.0","source":{"id":"2506.19848","kind":"arxiv","version":1}},"canonical_sha256":"75e7adc42463722e0c50a698c5b8eb89f4936579671beaac6de686adf4a0fb94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75e7adc42463722e0c50a698c5b8eb89f4936579671beaac6de686adf4a0fb94","first_computed_at":"2026-07-05T11:26:39.512416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:39.512416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yxIRn/Q6diO4rY7hDI2WkTQ2vnbRyTA7qwUOJ7rdBUptov/4rqG1ZjdZja3d1A6iDRE3WtH1S2luyTPL1lnaDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:39.512898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1f89cc53fd6f2b1d79d28d699a64936624db220552f87c6c6dd967c6652a9fe","sha256:79deead5e90a6cdd5b89a6a61eb9323ce627f0384e4de1c45d00a723c53919b7"],"state_sha256":"8ad9639895efc8520f3e5f98a9a9f5e8cbe7fae152f0d9c6e7106d2fa55b8d14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tUzVsDQ4JPYiQcnrDs/iDcO7cUWXrBenpKenztqg4pKKBpDVppZBUCa1uBY97Px19FAvRrngkaR5cXLuQQwfDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T09:09:46.226499Z","bundle_sha256":"4fa5366157df72d2814d7c021f71ccc64f05ad25f5778cdf390d207a1fd151b0"}}