{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3FFYFODFZPHPMJNZGFWZO4Q2A7","short_pith_number":"pith:3FFYFODF","canonical_record":{"source":{"id":"2412.11836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T14:57:40Z","cross_cats_sorted":[],"title_canon_sha256":"5595f3b93664a67958316ce05a2ec50f4e1727f9debe7e28ae9e6488f13b3025","abstract_canon_sha256":"5ca4b6d5f9ecc469083dca2009e143fbca95bb877a2f7b1ad11a718fbfec0283"},"schema_version":"1.0"},"canonical_sha256":"d94b82b865cbcef625b9316d97721a07d9878f567fb92c9a193e75361f3d655e","source":{"kind":"arxiv","id":"2412.11836","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11836","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11836v1","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11836","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"3FFYFODFZPHP","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"pith_short_16","alias_value":"3FFYFODFZPHPMJNZ","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"pith_short_8","alias_value":"3FFYFODF","created_at":"2026-07-05T09:49:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3FFYFODFZPHPMJNZGFWZO4Q2A7","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T14:57:40Z","cross_cats_sorted":[],"title_canon_sha256":"5595f3b93664a67958316ce05a2ec50f4e1727f9debe7e28ae9e6488f13b3025","abstract_canon_sha256":"5ca4b6d5f9ecc469083dca2009e143fbca95bb877a2f7b1ad11a718fbfec0283"},"schema_version":"1.0"},"canonical_sha256":"d94b82b865cbcef625b9316d97721a07d9878f567fb92c9a193e75361f3d655e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:52.358351Z","signature_b64":"66w7CY8w5McEcSb8ps5DTnLjgMBV85SBwnNE0+vQ79k+ImIsaAq3+jh1EXRnHe83rgLRu0nIt1KDvwPLFDOhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d94b82b865cbcef625b9316d97721a07d9878f567fb92c9a193e75361f3d655e","last_reissued_at":"2026-07-05T09:49:52.357816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:52.357816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11836","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":"2026-07-05T09:49:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7d4C6CqSt3tIoHM+dPWE+VZ+nRbjYEXkoA4etpsf66j86RiZMPALfR7iThLBuC5X4OVam9qJyloVRrBLkGpJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:36:44.361016Z"},"content_sha256":"3ce5a0280a7a510fcca7fb84314b05b392be4c688950c869e9b1d88e75df1597","schema_version":"1.0","event_id":"sha256:3ce5a0280a7a510fcca7fb84314b05b392be4c688950c869e9b1d88e75df1597"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3FFYFODFZPHPMJNZGFWZO4Q2A7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UnMA-CapSumT: Unified and Multi-Head Attention-driven Caption Summarization Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chhavi Dhiman, Dhruv Sharma, Dinesh Kumar","submitted_at":"2024-12-16T14:57:40Z","abstract_excerpt":"Image captioning is the generation of natural language descriptions of images which have increased immense popularity in the recent past. With this different deep-learning techniques are devised for the development of factual and stylized image captioning models. Previous models focused more on the generation of factual and stylized captions separately providing more than one caption for a single image. The descriptions generated from these suffer from out-of-vocabulary and repetition issues. To the best of our knowledge, no such work exists that provided a description that integrates differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11836","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/2412.11836/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":"2026-07-05T09:49:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bp26LJPjMGOe+yad+vBubTpSQ8vleF7k1kWzd6na0cmeS/WHHwa37TPaPEcf3SlK3xsVfxsmNlv8p8D+fNDFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:36:44.361526Z"},"content_sha256":"baedd6971da6c03ad5ce69a0e33d9fae6e77454468f4983371a0d188bb0dffcf","schema_version":"1.0","event_id":"sha256:baedd6971da6c03ad5ce69a0e33d9fae6e77454468f4983371a0d188bb0dffcf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3FFYFODFZPHPMJNZGFWZO4Q2A7/bundle.json","state_url":"https://pith.science/pith/3FFYFODFZPHPMJNZGFWZO4Q2A7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3FFYFODFZPHPMJNZGFWZO4Q2A7/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":"2026-08-15T17:36:44Z","links":{"resolver":"https://pith.science/pith/3FFYFODFZPHPMJNZGFWZO4Q2A7","bundle":"https://pith.science/pith/3FFYFODFZPHPMJNZGFWZO4Q2A7/bundle.json","state":"https://pith.science/pith/3FFYFODFZPHPMJNZGFWZO4Q2A7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3FFYFODFZPHPMJNZGFWZO4Q2A7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3FFYFODFZPHPMJNZGFWZO4Q2A7","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":"5ca4b6d5f9ecc469083dca2009e143fbca95bb877a2f7b1ad11a718fbfec0283","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T14:57:40Z","title_canon_sha256":"5595f3b93664a67958316ce05a2ec50f4e1727f9debe7e28ae9e6488f13b3025"},"schema_version":"1.0","source":{"id":"2412.11836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11836","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11836v1","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11836","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"3FFYFODFZPHP","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"pith_short_16","alias_value":"3FFYFODFZPHPMJNZ","created_at":"2026-07-05T09:49:52Z"},{"alias_kind":"pith_short_8","alias_value":"3FFYFODF","created_at":"2026-07-05T09:49:52Z"}],"graph_snapshots":[{"event_id":"sha256:baedd6971da6c03ad5ce69a0e33d9fae6e77454468f4983371a0d188bb0dffcf","target":"graph","created_at":"2026-07-05T09:49:52Z","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/2412.11836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning is the generation of natural language descriptions of images which have increased immense popularity in the recent past. With this different deep-learning techniques are devised for the development of factual and stylized image captioning models. Previous models focused more on the generation of factual and stylized captions separately providing more than one caption for a single image. The descriptions generated from these suffer from out-of-vocabulary and repetition issues. To the best of our knowledge, no such work exists that provided a description that integrates differen","authors_text":"Chhavi Dhiman, Dhruv Sharma, Dinesh Kumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T14:57:40Z","title":"UnMA-CapSumT: Unified and Multi-Head Attention-driven Caption Summarization Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11836","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":"sha256:3ce5a0280a7a510fcca7fb84314b05b392be4c688950c869e9b1d88e75df1597","target":"record","created_at":"2026-07-05T09:49:52Z","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":"5ca4b6d5f9ecc469083dca2009e143fbca95bb877a2f7b1ad11a718fbfec0283","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T14:57:40Z","title_canon_sha256":"5595f3b93664a67958316ce05a2ec50f4e1727f9debe7e28ae9e6488f13b3025"},"schema_version":"1.0","source":{"id":"2412.11836","kind":"arxiv","version":1}},"canonical_sha256":"d94b82b865cbcef625b9316d97721a07d9878f567fb92c9a193e75361f3d655e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d94b82b865cbcef625b9316d97721a07d9878f567fb92c9a193e75361f3d655e","first_computed_at":"2026-07-05T09:49:52.357816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:52.357816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"66w7CY8w5McEcSb8ps5DTnLjgMBV85SBwnNE0+vQ79k+ImIsaAq3+jh1EXRnHe83rgLRu0nIt1KDvwPLFDOhBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:52.358351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ce5a0280a7a510fcca7fb84314b05b392be4c688950c869e9b1d88e75df1597","sha256:baedd6971da6c03ad5ce69a0e33d9fae6e77454468f4983371a0d188bb0dffcf"],"state_sha256":"2e824ad9a5c925c0e51c003fec09eb21f3b0e9e7ad7188d817a4974f8366c3f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Id+qzqIjx9TdyGd4/nsz9AWOmO9LUUWEksxeGA3AytU6ODvcGoecRmMD9//WC7gxrWINneJFLFf36QjRa4GLCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:36:44.366554Z","bundle_sha256":"10e0552ead42c36180eab7e426179266902a9ac96712300eea68de9dbed25a91"}}