{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KJ2ETX3ND7REP56IZK4DMNLPWF","short_pith_number":"pith:KJ2ETX3N","canonical_record":{"source":{"id":"2302.04858","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-09T18:57:56Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"21bf5a84e1da7bfcdc68c124299e253309686322a05efa3853478420f391d463","abstract_canon_sha256":"b5bfbd4f1233801abd828dbf6f3e3c3fd7b9c435307ff26dcae0ab024f2d5714"},"schema_version":"1.0"},"canonical_sha256":"527449df6d1fe247f7c8cab836356fb1439f0907c6908f341cb28b1bbabf7eb7","source":{"kind":"arxiv","id":"2302.04858","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04858","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04858v2","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04858","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"KJ2ETX3ND7RE","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"KJ2ETX3ND7REP56I","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"KJ2ETX3N","created_at":"2026-07-05T07:03:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KJ2ETX3ND7REP56IZK4DMNLPWF","target":"record","payload":{"canonical_record":{"source":{"id":"2302.04858","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-09T18:57:56Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"21bf5a84e1da7bfcdc68c124299e253309686322a05efa3853478420f391d463","abstract_canon_sha256":"b5bfbd4f1233801abd828dbf6f3e3c3fd7b9c435307ff26dcae0ab024f2d5714"},"schema_version":"1.0"},"canonical_sha256":"527449df6d1fe247f7c8cab836356fb1439f0907c6908f341cb28b1bbabf7eb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:20.718602Z","signature_b64":"EgZLxN4FHv4z3MZgwKyQytIJCE/cvavqVBiThwBOy0Ue1K5qRVj0CsSVMuTdFuh0Dx2Jf8h2tluawIVxmuJLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"527449df6d1fe247f7c8cab836356fb1439f0907c6908f341cb28b1bbabf7eb7","last_reissued_at":"2026-07-05T07:03:20.718120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:20.718120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.04858","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":"2026-07-05T07:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/edesIlvubNdn1P3hD/x6f+8+XcpOhbn7ueihplP+3XC3OCjmgwaFbP907fxGMsz7I725sqYqkdakc7wAxlUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:37:40.374991Z"},"content_sha256":"324801a204fd9c71472afe42085554b4e83630809475b0dda217996822358f3e","schema_version":"1.0","event_id":"sha256:324801a204fd9c71472afe42085554b4e83630809475b0dda217996822358f3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KJ2ETX3ND7REP56IZK4DMNLPWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Bo Li, Bryan Catanzaro, Chaowei Xiao, De-An Huang, Linxi Fan, Ming-Yu Liu, Mohammad Shoeybi, Shiyi Lan, Vijay Korthikanti, Weili Nie, Wei Ping, Yuke Zhu, Zhiding Yu, Zhuolin Yang, Zihan Liu","submitted_at":"2023-02-09T18:57:56Z","abstract_excerpt":"Augmenting pretrained language models (LMs) with a vision encoder (e.g., Flamingo) has obtained the state-of-the-art results in image-to-text generation. However, these models store all the knowledge within their parameters, thus often requiring enormous model parameters to model the abundant visual concepts and very rich textual descriptions. Additionally, they are inefficient in incorporating new data, requiring a computational-expensive fine-tuning process. In this work, we introduce a Retrieval-augmented Visual Language Model, Re-ViLM, built upon the Flamingo, that supports retrieving the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04858","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/2302.04858/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":"2026-07-05T07:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7f5gJClhitMF5Sh8k7PUYSuUxlpYEgWz7zUY4tDYIDWqt9nRUSP55M8zgM2nQSO8SMMhy8jXBAXHSOxPItZ/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:37:40.375401Z"},"content_sha256":"8e71b832555bf665bb28ffa79b2d0790055630743dcfb8af7dc02936cef350db","schema_version":"1.0","event_id":"sha256:8e71b832555bf665bb28ffa79b2d0790055630743dcfb8af7dc02936cef350db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJ2ETX3ND7REP56IZK4DMNLPWF/bundle.json","state_url":"https://pith.science/pith/KJ2ETX3ND7REP56IZK4DMNLPWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJ2ETX3ND7REP56IZK4DMNLPWF/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":"2026-07-06T20:37:40Z","links":{"resolver":"https://pith.science/pith/KJ2ETX3ND7REP56IZK4DMNLPWF","bundle":"https://pith.science/pith/KJ2ETX3ND7REP56IZK4DMNLPWF/bundle.json","state":"https://pith.science/pith/KJ2ETX3ND7REP56IZK4DMNLPWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJ2ETX3ND7REP56IZK4DMNLPWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KJ2ETX3ND7REP56IZK4DMNLPWF","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":"b5bfbd4f1233801abd828dbf6f3e3c3fd7b9c435307ff26dcae0ab024f2d5714","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-09T18:57:56Z","title_canon_sha256":"21bf5a84e1da7bfcdc68c124299e253309686322a05efa3853478420f391d463"},"schema_version":"1.0","source":{"id":"2302.04858","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04858","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04858v2","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04858","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"KJ2ETX3ND7RE","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"KJ2ETX3ND7REP56I","created_at":"2026-07-05T07:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"KJ2ETX3N","created_at":"2026-07-05T07:03:20Z"}],"graph_snapshots":[{"event_id":"sha256:8e71b832555bf665bb28ffa79b2d0790055630743dcfb8af7dc02936cef350db","target":"graph","created_at":"2026-07-05T07:03:20Z","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/2302.04858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Augmenting pretrained language models (LMs) with a vision encoder (e.g., Flamingo) has obtained the state-of-the-art results in image-to-text generation. However, these models store all the knowledge within their parameters, thus often requiring enormous model parameters to model the abundant visual concepts and very rich textual descriptions. Additionally, they are inefficient in incorporating new data, requiring a computational-expensive fine-tuning process. In this work, we introduce a Retrieval-augmented Visual Language Model, Re-ViLM, built upon the Flamingo, that supports retrieving the ","authors_text":"Anima Anandkumar, Bo Li, Bryan Catanzaro, Chaowei Xiao, De-An Huang, Linxi Fan, Ming-Yu Liu, Mohammad Shoeybi, Shiyi Lan, Vijay Korthikanti, Weili Nie, Wei Ping, Yuke Zhu, Zhiding Yu, Zhuolin Yang, Zihan Liu","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-09T18:57:56Z","title":"Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04858","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":"sha256:324801a204fd9c71472afe42085554b4e83630809475b0dda217996822358f3e","target":"record","created_at":"2026-07-05T07:03:20Z","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":"b5bfbd4f1233801abd828dbf6f3e3c3fd7b9c435307ff26dcae0ab024f2d5714","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-09T18:57:56Z","title_canon_sha256":"21bf5a84e1da7bfcdc68c124299e253309686322a05efa3853478420f391d463"},"schema_version":"1.0","source":{"id":"2302.04858","kind":"arxiv","version":2}},"canonical_sha256":"527449df6d1fe247f7c8cab836356fb1439f0907c6908f341cb28b1bbabf7eb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"527449df6d1fe247f7c8cab836356fb1439f0907c6908f341cb28b1bbabf7eb7","first_computed_at":"2026-07-05T07:03:20.718120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:20.718120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EgZLxN4FHv4z3MZgwKyQytIJCE/cvavqVBiThwBOy0Ue1K5qRVj0CsSVMuTdFuh0Dx2Jf8h2tluawIVxmuJLCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:20.718602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.04858","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:324801a204fd9c71472afe42085554b4e83630809475b0dda217996822358f3e","sha256:8e71b832555bf665bb28ffa79b2d0790055630743dcfb8af7dc02936cef350db"],"state_sha256":"dd50e131a7ff4ff50e62036f51c9175a42845b059ab2d347a8038c393dfb14b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n3CvIwwGN+oG/1HCYzQMprdLE4sREQeh3Bl1eMwWlApP5t4D2fUpU+CfgAtX/8Vgs9Kch5cb/sWwzmIytS1pBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:37:40.377861Z","bundle_sha256":"12e6b66f8fec6520bd562d8efc21ed03062569df46e4769998c40c67bdb1d82e"}}