{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KMX6ULIBS46LKFZ7YCUPAO5KBL","short_pith_number":"pith:KMX6ULIB","canonical_record":{"source":{"id":"2502.01507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T16:40:47Z","cross_cats_sorted":[],"title_canon_sha256":"253824af95505b8c2314dec569a66fd5239225adbc4a79b0f87d9b0862d63ecc","abstract_canon_sha256":"29147e2360873f3f4dd6918436203ae88902b5e3ee8ec7feeb419aca587b91f1"},"schema_version":"1.0"},"canonical_sha256":"532fea2d01973cb5173fc0a8f03baa0adc8c740987151716e5d50688eae1167a","source":{"kind":"arxiv","id":"2502.01507","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01507","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01507v1","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01507","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"KMX6ULIBS46L","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"KMX6ULIBS46LKFZ7","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"KMX6ULIB","created_at":"2026-07-05T10:08:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KMX6ULIBS46LKFZ7YCUPAO5KBL","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T16:40:47Z","cross_cats_sorted":[],"title_canon_sha256":"253824af95505b8c2314dec569a66fd5239225adbc4a79b0f87d9b0862d63ecc","abstract_canon_sha256":"29147e2360873f3f4dd6918436203ae88902b5e3ee8ec7feeb419aca587b91f1"},"schema_version":"1.0"},"canonical_sha256":"532fea2d01973cb5173fc0a8f03baa0adc8c740987151716e5d50688eae1167a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:56.055067Z","signature_b64":"XJ/uEMdDL5OAE18RBelcRjNYqLs93xt/jdqzqfnfLOXyD0IL9QADUMDWXqNiVm6pkyzoKRSJtx/T2b/H8/IECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"532fea2d01973cb5173fc0a8f03baa0adc8c740987151716e5d50688eae1167a","last_reissued_at":"2026-07-05T10:08:56.054598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:56.054598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01507","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":"2026-07-05T10:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ph0ObMQPquMNskdQct7g2eVlA2DM2OQbY0quqjYNytdcKlgj/wf0DR+2nnnR93cewj+iy3+i+L5MwCykhprcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:21:43.553802Z"},"content_sha256":"44087d5216f429b393ad40944ce27f7d6e5cfa96afe7b423eb3f79bbd187b5fa","schema_version":"1.0","event_id":"sha256:44087d5216f429b393ad40944ce27f7d6e5cfa96afe7b423eb3f79bbd187b5fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KMX6ULIBS46LKFZ7YCUPAO5KBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Mittal, Yeruru Asrar Ahmed","submitted_at":"2025-02-03T16:40:47Z","abstract_excerpt":"Text-to-Image (T2I) synthesis is a challenging task that requires modeling complex interactions between two modalities ( i.e., text and image). A common framework adopted in recent state-of-the-art approaches to achieving such multimodal interactions is to bootstrap the learning process with pre-trained image-aligned text embeddings trained using contrastive loss. Furthermore, these embeddings are typically trained generically and reused across various synthesis models. In contrast, we explore an approach to learning text embeddings specifically tailored to the T2I synthesis network, trained i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01507","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/2502.01507/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":"2026-07-05T10:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uiPE4mNInkSOnBRR0RXkWDtbWnQpEP3+knk3e11rgnoTRd6jdv/3V+q/gs+u7x9BGWilIQWtBPN3MKtoTOsCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:21:43.557535Z"},"content_sha256":"51d0498662fed0d1621ccde612c821667fc888f33bf9b08a728cdf372a2be719","schema_version":"1.0","event_id":"sha256:51d0498662fed0d1621ccde612c821667fc888f33bf9b08a728cdf372a2be719"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KMX6ULIBS46LKFZ7YCUPAO5KBL/bundle.json","state_url":"https://pith.science/pith/KMX6ULIBS46LKFZ7YCUPAO5KBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KMX6ULIBS46LKFZ7YCUPAO5KBL/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":"2026-08-17T20:21:43Z","links":{"resolver":"https://pith.science/pith/KMX6ULIBS46LKFZ7YCUPAO5KBL","bundle":"https://pith.science/pith/KMX6ULIBS46LKFZ7YCUPAO5KBL/bundle.json","state":"https://pith.science/pith/KMX6ULIBS46LKFZ7YCUPAO5KBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KMX6ULIBS46LKFZ7YCUPAO5KBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KMX6ULIBS46LKFZ7YCUPAO5KBL","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":"29147e2360873f3f4dd6918436203ae88902b5e3ee8ec7feeb419aca587b91f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T16:40:47Z","title_canon_sha256":"253824af95505b8c2314dec569a66fd5239225adbc4a79b0f87d9b0862d63ecc"},"schema_version":"1.0","source":{"id":"2502.01507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01507","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01507v1","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01507","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"KMX6ULIBS46L","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"KMX6ULIBS46LKFZ7","created_at":"2026-07-05T10:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"KMX6ULIB","created_at":"2026-07-05T10:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:51d0498662fed0d1621ccde612c821667fc888f33bf9b08a728cdf372a2be719","target":"graph","created_at":"2026-07-05T10:08:56Z","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/2502.01507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-Image (T2I) synthesis is a challenging task that requires modeling complex interactions between two modalities ( i.e., text and image). A common framework adopted in recent state-of-the-art approaches to achieving such multimodal interactions is to bootstrap the learning process with pre-trained image-aligned text embeddings trained using contrastive loss. Furthermore, these embeddings are typically trained generically and reused across various synthesis models. In contrast, we explore an approach to learning text embeddings specifically tailored to the T2I synthesis network, trained i","authors_text":"Anurag Mittal, Yeruru Asrar Ahmed","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T16:40:47Z","title":"End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01507","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":"sha256:44087d5216f429b393ad40944ce27f7d6e5cfa96afe7b423eb3f79bbd187b5fa","target":"record","created_at":"2026-07-05T10:08:56Z","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":"29147e2360873f3f4dd6918436203ae88902b5e3ee8ec7feeb419aca587b91f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T16:40:47Z","title_canon_sha256":"253824af95505b8c2314dec569a66fd5239225adbc4a79b0f87d9b0862d63ecc"},"schema_version":"1.0","source":{"id":"2502.01507","kind":"arxiv","version":1}},"canonical_sha256":"532fea2d01973cb5173fc0a8f03baa0adc8c740987151716e5d50688eae1167a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"532fea2d01973cb5173fc0a8f03baa0adc8c740987151716e5d50688eae1167a","first_computed_at":"2026-07-05T10:08:56.054598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:56.054598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJ/uEMdDL5OAE18RBelcRjNYqLs93xt/jdqzqfnfLOXyD0IL9QADUMDWXqNiVm6pkyzoKRSJtx/T2b/H8/IECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:56.055067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44087d5216f429b393ad40944ce27f7d6e5cfa96afe7b423eb3f79bbd187b5fa","sha256:51d0498662fed0d1621ccde612c821667fc888f33bf9b08a728cdf372a2be719"],"state_sha256":"fccb4ae3fc4bee381f6af2117a918bcd4c0e475d59bed0ffc17b73ed5d77bb2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SnJKrgBCfDwNpixVBuYNzKZzh/1tC2bMkLWnTqL8tPruOKdXD3Lg8GYbQ4vmJlBZnV2d/B/HLgUW969EDqLGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:21:43.594661Z","bundle_sha256":"0d2fec9ef595f2bf97199c185504f892d6077621bddda55f1bf6b90f21749102"}}