{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XIUEWZ2HJC423OFGYMPWNNOFFW","short_pith_number":"pith:XIUEWZ2H","canonical_record":{"source":{"id":"2401.01076","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T07:40:12Z","cross_cats_sorted":[],"title_canon_sha256":"db8a7544769840255ae3089c75bdf79fdd1e254d7e984c911fdae23461e856fc","abstract_canon_sha256":"871e750ae669ea2f51f2f20444e8be02ec6e3a2ab06e7cc0c0d97e7722e3a29a"},"schema_version":"1.0"},"canonical_sha256":"ba284b674748b9adb8a6c31f66b5c52da5336e632ce27cced8ccff4ac9900535","source":{"kind":"arxiv","id":"2401.01076","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01076","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01076v2","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01076","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"pith_short_12","alias_value":"XIUEWZ2HJC42","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"pith_short_16","alias_value":"XIUEWZ2HJC423OFG","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"pith_short_8","alias_value":"XIUEWZ2H","created_at":"2026-07-05T07:29:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XIUEWZ2HJC423OFGYMPWNNOFFW","target":"record","payload":{"canonical_record":{"source":{"id":"2401.01076","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T07:40:12Z","cross_cats_sorted":[],"title_canon_sha256":"db8a7544769840255ae3089c75bdf79fdd1e254d7e984c911fdae23461e856fc","abstract_canon_sha256":"871e750ae669ea2f51f2f20444e8be02ec6e3a2ab06e7cc0c0d97e7722e3a29a"},"schema_version":"1.0"},"canonical_sha256":"ba284b674748b9adb8a6c31f66b5c52da5336e632ce27cced8ccff4ac9900535","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:41.386334Z","signature_b64":"psZ3E8MCdPeP/u7wo92EBDtqSP4zWRgiA6GYJucGByNerahv73xoufuspfZ29Pcblx3FdJswYjfnTVfzsI2KAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba284b674748b9adb8a6c31f66b5c52da5336e632ce27cced8ccff4ac9900535","last_reissued_at":"2026-07-05T07:29:41.385926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:41.385926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.01076","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":"2026-07-05T07:29:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ZbOLclWM80IpNMNDYhL/E3xny6uIqC9BaKpoXI3kTy7LDY5c67sYloWEIOh40e3Ui8KbsDJwHdUvfyj4x/iAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:37:45.985480Z"},"content_sha256":"c6a78655ed585b1b90ac41966b0a206e2a45155384b090176f0fb124a3b584d3","schema_version":"1.0","event_id":"sha256:c6a78655ed585b1b90ac41966b0a206e2a45155384b090176f0fb124a3b584d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XIUEWZ2HJC423OFGYMPWNNOFFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Fei Huang, Min Yang, Yongbin Li, Zhichao Yin","submitted_at":"2024-01-02T07:40:12Z","abstract_excerpt":"Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems. These models have demonstrated significant improvements by fine-tuning on downstream tasks. However, the existing pre-trained models primarily focus on effectively capturing the alignment between vision and language modalities, often ignoring the intricate nature of dialog context. In this paper, we propose a parameter-efficient prompt-tuning method named DialCLIP for multi-modal dialog retrieval. Specifically, our approach introduces a multi-modal cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01076","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/2401.01076/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":"2026-07-05T07:29:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YB6HzUhBDNWCqCc5CRtaR7k11caFcWk/ln2tl41hn9aK4csaBTSj0b+inQxjwtMXn4OHKegrEJ2Rt1MPMz4cCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:37:45.986054Z"},"content_sha256":"8f841550eafa484480ee60d0bab1e40e2b8d9d6af696607183cf6ec9b6da1f48","schema_version":"1.0","event_id":"sha256:8f841550eafa484480ee60d0bab1e40e2b8d9d6af696607183cf6ec9b6da1f48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/bundle.json","state_url":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/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":"2026-08-04T10:37:45Z","links":{"resolver":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW","bundle":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/bundle.json","state":"https://pith.science/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XIUEWZ2HJC423OFGYMPWNNOFFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XIUEWZ2HJC423OFGYMPWNNOFFW","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":"871e750ae669ea2f51f2f20444e8be02ec6e3a2ab06e7cc0c0d97e7722e3a29a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T07:40:12Z","title_canon_sha256":"db8a7544769840255ae3089c75bdf79fdd1e254d7e984c911fdae23461e856fc"},"schema_version":"1.0","source":{"id":"2401.01076","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01076","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01076v2","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01076","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"pith_short_12","alias_value":"XIUEWZ2HJC42","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"pith_short_16","alias_value":"XIUEWZ2HJC423OFG","created_at":"2026-07-05T07:29:41Z"},{"alias_kind":"pith_short_8","alias_value":"XIUEWZ2H","created_at":"2026-07-05T07:29:41Z"}],"graph_snapshots":[{"event_id":"sha256:8f841550eafa484480ee60d0bab1e40e2b8d9d6af696607183cf6ec9b6da1f48","target":"graph","created_at":"2026-07-05T07:29:41Z","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/2401.01076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems. These models have demonstrated significant improvements by fine-tuning on downstream tasks. However, the existing pre-trained models primarily focus on effectively capturing the alignment between vision and language modalities, often ignoring the intricate nature of dialog context. In this paper, we propose a parameter-efficient prompt-tuning method named DialCLIP for multi-modal dialog retrieval. Specifically, our approach introduces a multi-modal cont","authors_text":"Binyuan Hui, Fei Huang, Min Yang, Yongbin Li, Zhichao Yin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T07:40:12Z","title":"DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01076","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:c6a78655ed585b1b90ac41966b0a206e2a45155384b090176f0fb124a3b584d3","target":"record","created_at":"2026-07-05T07:29:41Z","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":"871e750ae669ea2f51f2f20444e8be02ec6e3a2ab06e7cc0c0d97e7722e3a29a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T07:40:12Z","title_canon_sha256":"db8a7544769840255ae3089c75bdf79fdd1e254d7e984c911fdae23461e856fc"},"schema_version":"1.0","source":{"id":"2401.01076","kind":"arxiv","version":2}},"canonical_sha256":"ba284b674748b9adb8a6c31f66b5c52da5336e632ce27cced8ccff4ac9900535","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba284b674748b9adb8a6c31f66b5c52da5336e632ce27cced8ccff4ac9900535","first_computed_at":"2026-07-05T07:29:41.385926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:41.385926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"psZ3E8MCdPeP/u7wo92EBDtqSP4zWRgiA6GYJucGByNerahv73xoufuspfZ29Pcblx3FdJswYjfnTVfzsI2KAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:41.386334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01076","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6a78655ed585b1b90ac41966b0a206e2a45155384b090176f0fb124a3b584d3","sha256:8f841550eafa484480ee60d0bab1e40e2b8d9d6af696607183cf6ec9b6da1f48"],"state_sha256":"c4c177ac222b829709e9c4cbc94c3090b60d443c9bfa36913c6259a6051f0d00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3VjEGaf+1PPOaA9B7J3SlNsKAaHGDDik3heRTn5Ux9RPWcxZ9b0UZ1EQ3L06lu3eyFrBWzp02MBvooTW1HczCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:37:45.991559Z","bundle_sha256":"e30d88a9e8404db03ec5da2a9e0629bfdbda9e636af330236facfbb29204f2dd"}}