{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QGE7B7WBWH2BGQ4ULPRE2ZC2ST","short_pith_number":"pith:QGE7B7WB","schema_version":"1.0","canonical_sha256":"8189f0fec1b1f41343945be24d645a94da58bc5e85a5319b1f237acc480add59","source":{"kind":"arxiv","id":"2302.01328","version":3},"attestation_state":"computed","paper":{"title":"IC3: Image Captioning by Committee Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Austin Myers, David A. Ross, David M. Chan, John Canny, Sudheendra Vijayanarasimhan","submitted_at":"2023-02-02T18:58:05Z","abstract_excerpt":"If you ask a human to describe an image, they might do so in a thousand different ways. Traditionally, image captioning models are trained to generate a single \"best\" (most like a reference) image caption. Unfortunately, doing so encourages captions that are \"informationally impoverished,\" and focus on only a subset of the possible details, while ignoring other potentially useful information in the scene. In this work, we introduce a simple, yet novel, method: \"Image Captioning by Committee Consensus\" (IC3), designed to generate a single caption that captures high-level details from several an"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.01328","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-02T18:58:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"5bd454da63a5a28fbe9d8cb433ac5bc9581632df2239b1810e405d3bd3559970","abstract_canon_sha256":"84a58038f8b88c39a84898a7114cbf5bbdac6958e7b1715082afc34430d9089e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:27.161749Z","signature_b64":"Dj9NcfXTB5CYrARuUCU9ko+X2F59SowWI/rd0x1Ijs1l4oKdBqBKPYmrVtXdI/bs4tAl1tMKgVLuJZyl1ShMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8189f0fec1b1f41343945be24d645a94da58bc5e85a5319b1f237acc480add59","last_reissued_at":"2026-07-05T07:02:27.161335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:27.161335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IC3: Image Captioning by Committee Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Austin Myers, David A. Ross, David M. Chan, John Canny, Sudheendra Vijayanarasimhan","submitted_at":"2023-02-02T18:58:05Z","abstract_excerpt":"If you ask a human to describe an image, they might do so in a thousand different ways. Traditionally, image captioning models are trained to generate a single \"best\" (most like a reference) image caption. Unfortunately, doing so encourages captions that are \"informationally impoverished,\" and focus on only a subset of the possible details, while ignoring other potentially useful information in the scene. In this work, we introduce a simple, yet novel, method: \"Image Captioning by Committee Consensus\" (IC3), designed to generate a single caption that captures high-level details from several an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01328","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/2302.01328/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.01328","created_at":"2026-07-05T07:02:27.161395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01328v3","created_at":"2026-07-05T07:02:27.161395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01328","created_at":"2026-07-05T07:02:27.161395+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGE7B7WBWH2B","created_at":"2026-07-05T07:02:27.161395+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGE7B7WBWH2BGQ4U","created_at":"2026-07-05T07:02:27.161395+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGE7B7WB","created_at":"2026-07-05T07:02:27.161395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16716","citing_title":"Enhancing Remote Sensing Vision-Language Models Through MLLM and LLM-Based High-Quality Image-Text Dataset Generation","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST","json":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST.json","graph_json":"https://pith.science/api/pith-number/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/graph.json","events_json":"https://pith.science/api/pith-number/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/events.json","paper":"https://pith.science/paper/QGE7B7WB"},"agent_actions":{"view_html":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST","download_json":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST.json","view_paper":"https://pith.science/paper/QGE7B7WB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01328&json=true","fetch_graph":"https://pith.science/api/pith-number/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/graph.json","fetch_events":"https://pith.science/api/pith-number/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/action/storage_attestation","attest_author":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/action/author_attestation","sign_citation":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/action/citation_signature","submit_replication":"https://pith.science/pith/QGE7B7WBWH2BGQ4ULPRE2ZC2ST/action/replication_record"}},"created_at":"2026-07-05T07:02:27.161395+00:00","updated_at":"2026-07-05T07:02:27.161395+00:00"}