{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CF5MIOSGXMF5BJXSP4RLLN7TE7","short_pith_number":"pith:CF5MIOSG","canonical_record":{"source":{"id":"2504.16072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:51:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"296424ccf4248476dc53dd220e8e22c5b445e497f764b52938460bb92b2cc12e","abstract_canon_sha256":"71a909d979c9815ca7b132cb907a312a8fd65d0d2b82e64f3affb060606df25e"},"schema_version":"1.0"},"canonical_sha256":"117ac43a46bb0bd0a6f27f22b5b7f327dca2bb869387a7d0bb04787f2fc11614","source":{"kind":"arxiv","id":"2504.16072","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16072","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16072v1","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16072","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"CF5MIOSGXMF5","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_16","alias_value":"CF5MIOSGXMF5BJXS","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_8","alias_value":"CF5MIOSG","created_at":"2026-07-05T10:52:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CF5MIOSGXMF5BJXSP4RLLN7TE7","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:51:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"296424ccf4248476dc53dd220e8e22c5b445e497f764b52938460bb92b2cc12e","abstract_canon_sha256":"71a909d979c9815ca7b132cb907a312a8fd65d0d2b82e64f3affb060606df25e"},"schema_version":"1.0"},"canonical_sha256":"117ac43a46bb0bd0a6f27f22b5b7f327dca2bb869387a7d0bb04787f2fc11614","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:35.041244Z","signature_b64":"qSSK/W87QpSOvEhzC+KCoIlot3j54Swjaowp9GvjGHjj5+WMuOCw5Ka4FvoGjDMoxA55cW6hFb9HEEAu4xYLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"117ac43a46bb0bd0a6f27f22b5b7f327dca2bb869387a7d0bb04787f2fc11614","last_reissued_at":"2026-07-05T10:52:35.040787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:35.040787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16072","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":"2026-07-05T10:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r0ybNoL4wLTNWH0rXgK8WZeyyhnGVQEYT6Ly/ASg+akBmKULLgiEMY4Y5MPC+A+pG4gtK/WLJK91amFd5DCmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:12:25.945310Z"},"content_sha256":"d1135f626b6dee77a9484c17927e686e2daba64274f5ae2c6322711823ded32d","schema_version":"1.0","event_id":"sha256:d1135f626b6dee77a9484c17927e686e2daba64274f5ae2c6322711823ded32d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CF5MIOSGXMF5BJXSP4RLLN7TE7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Describe Anything: Detailed Localized Image and Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adam Yala, Boyi Li, Hanzi Mao, Long Lian, Marco Pavone, Ming-Yu Liu, Sifei Liu, Trevor Darrell, Yifan Ding, Yin Cui, Yunhao Ge","submitted_at":"2025-04-22T17:51:41Z","abstract_excerpt":"Generating detailed and accurate descriptions for specific regions in images and videos remains a fundamental challenge for vision-language models. We introduce the Describe Anything Model (DAM), a model designed for detailed localized captioning (DLC). DAM preserves both local details and global context through two key innovations: a focal prompt, which ensures high-resolution encoding of targeted regions, and a localized vision backbone, which integrates precise localization with its broader context. To tackle the scarcity of high-quality DLC data, we propose a Semi-supervised learning (SSL)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16072","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/2504.16072/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":"2026-07-05T10:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LwyEYwCmj4GCsTuugaijqH7XUKFj87R/f1K2qnBftDuXKCJAk5fnQ9QfvU2lUSOO6w25uQCffTfTUrYOdXwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:12:25.945694Z"},"content_sha256":"b7ed6bd51dd7a0d02c9e96e230d80288795be6e188a6779912536b01e2b80491","schema_version":"1.0","event_id":"sha256:b7ed6bd51dd7a0d02c9e96e230d80288795be6e188a6779912536b01e2b80491"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CF5MIOSGXMF5BJXSP4RLLN7TE7/bundle.json","state_url":"https://pith.science/pith/CF5MIOSGXMF5BJXSP4RLLN7TE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CF5MIOSGXMF5BJXSP4RLLN7TE7/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":"2026-07-09T04:12:25Z","links":{"resolver":"https://pith.science/pith/CF5MIOSGXMF5BJXSP4RLLN7TE7","bundle":"https://pith.science/pith/CF5MIOSGXMF5BJXSP4RLLN7TE7/bundle.json","state":"https://pith.science/pith/CF5MIOSGXMF5BJXSP4RLLN7TE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CF5MIOSGXMF5BJXSP4RLLN7TE7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CF5MIOSGXMF5BJXSP4RLLN7TE7","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":"71a909d979c9815ca7b132cb907a312a8fd65d0d2b82e64f3affb060606df25e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:51:41Z","title_canon_sha256":"296424ccf4248476dc53dd220e8e22c5b445e497f764b52938460bb92b2cc12e"},"schema_version":"1.0","source":{"id":"2504.16072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16072","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16072v1","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16072","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"CF5MIOSGXMF5","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_16","alias_value":"CF5MIOSGXMF5BJXS","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_8","alias_value":"CF5MIOSG","created_at":"2026-07-05T10:52:35Z"}],"graph_snapshots":[{"event_id":"sha256:b7ed6bd51dd7a0d02c9e96e230d80288795be6e188a6779912536b01e2b80491","target":"graph","created_at":"2026-07-05T10:52:35Z","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/2504.16072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating detailed and accurate descriptions for specific regions in images and videos remains a fundamental challenge for vision-language models. We introduce the Describe Anything Model (DAM), a model designed for detailed localized captioning (DLC). DAM preserves both local details and global context through two key innovations: a focal prompt, which ensures high-resolution encoding of targeted regions, and a localized vision backbone, which integrates precise localization with its broader context. To tackle the scarcity of high-quality DLC data, we propose a Semi-supervised learning (SSL)","authors_text":"Adam Yala, Boyi Li, Hanzi Mao, Long Lian, Marco Pavone, Ming-Yu Liu, Sifei Liu, Trevor Darrell, Yifan Ding, Yin Cui, Yunhao Ge","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:51:41Z","title":"Describe Anything: Detailed Localized Image and Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16072","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:d1135f626b6dee77a9484c17927e686e2daba64274f5ae2c6322711823ded32d","target":"record","created_at":"2026-07-05T10:52:35Z","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":"71a909d979c9815ca7b132cb907a312a8fd65d0d2b82e64f3affb060606df25e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:51:41Z","title_canon_sha256":"296424ccf4248476dc53dd220e8e22c5b445e497f764b52938460bb92b2cc12e"},"schema_version":"1.0","source":{"id":"2504.16072","kind":"arxiv","version":1}},"canonical_sha256":"117ac43a46bb0bd0a6f27f22b5b7f327dca2bb869387a7d0bb04787f2fc11614","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"117ac43a46bb0bd0a6f27f22b5b7f327dca2bb869387a7d0bb04787f2fc11614","first_computed_at":"2026-07-05T10:52:35.040787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:35.040787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qSSK/W87QpSOvEhzC+KCoIlot3j54Swjaowp9GvjGHjj5+WMuOCw5Ka4FvoGjDMoxA55cW6hFb9HEEAu4xYLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:35.041244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1135f626b6dee77a9484c17927e686e2daba64274f5ae2c6322711823ded32d","sha256:b7ed6bd51dd7a0d02c9e96e230d80288795be6e188a6779912536b01e2b80491"],"state_sha256":"e92a97c7049dd0fef23113293fd4530c9ebe322caaff891f04d93dbe6af10e9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OF0vQdVEHktn6Mv+MMy3ldH9iVDrCahZrVq2C7Zogrnfh98UL8d49HvDX3/QSSvReegTQl2DpIXhxOsvDaYSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:12:25.947751Z","bundle_sha256":"37756e99a0127a2e5f94c7b520f70affea761a93352ccca92ebdf3b508eaa604"}}